Legal dispute mediation plays a crucial role in resolving civil disputes, yet its empirical study is limited by privacy constraints and complex multivariate interactions. To address this limitation, we present AgentMediation, the first LLM-based agent framework for simulating dispute mediation. It simulates realistic mediation processes grounded in real-world disputes and enables controlled experimentation on key variables such as disputant strategies, dispute causes, and mediator expertise. Our empirical analysis reveals patterns consistent with sociological theories, including Group Polarization and Surface-level Consensus. As a comprehensive and extensible platform, AgentMediation paves the way for deeper integration of social science and AI in legal research.

The rapid development of large language models (LLMs) has highlighted the need for efficient and reliable methods to evaluate their performance. Traditional evaluation methods often face challenges like high costs, limited task formats, dependence on human references, and systematic biases. To address these limitations, we propose Auto-PRE, an automatic LLM evaluation framework inspired by the peer review process. Unlike previous approaches that rely on human annotations, Auto-PRE automatically selects evaluator LLMs based on three core traits: consistency, pertinence, and self-confidence, which correspond to the instruction, content, and response stages, respectively, and collectively cover the entire evaluation process. Experiments on three representative tasks, including summarization, non-factoid QA, and dialogue generation, demonstrate that Auto-PRE achieves state-of-the-art performance while significantly reducing evaluation costs. Furthermore, the structured and scalable design of our automatic qualification exam framework provides valuable insights into automating the evaluation of LLMs-as-judges, paving the way for more advanced LLM-based evaluation frameworks.

As large language models (LLMs) increasingly operate as autonomous agents in social contexts, evaluating their capacity for prosocial behavior is both theoretically and practically critical. However, existing research has primarily relied on static, economically framed paradigms, lacking models that capture the dynamic evolution of prosociality and its sensitivity to structural inequities. To address these gaps, we introduce ProSim, a simulation framework for modeling the prosocial behavior in LLM agents across diverse social conditions. We conduct three progressive studies to assess prosocial alignment. First, we demonstrate that LLM agents can exhibit human-like prosocial behavior across a broad range of real-world scenarios and adapt to normative policy interventions. Second, we find that agents engage in fairness-based third-party punishment and respond systematically to variations in inequity magnitude and enforcement cost. Third, we show that policy-induced inequities suppress prosocial behavior, propagate norm erosion through social networks. These findings advance prosocial behavior theory by elucidating how institutional dynamics shape the emergence, decay, and diffusion of prosocial norms in agent-driven societies.

Large language models (LLMs) are largely static and often redo reasoning or repeat mistakes.Prior experience reuse typically relies on external retrieval, which is similarity-based, can introduce noise, and adds latency.We introduce SEAM (Structured Experience Adapter Module), a lightweight, executor-specific plugin that stores experience in its parameters and generates a structured, instance-tailored experience entry in a single forward pass to guide a frozen LLM executor.SEAM is trained for utility via executor rollouts and GRPO while keeping the executor frozen, and can be further improved with logged-success SFT after deployment.Experiments on mathematical reasoning benchmarks show consistent accuracy gains across executors with low overhead.Extensive ablation and analysis further elucidate the mechanisms underlying SEAM's effectiveness and robustness. 1 † Equal contribution.

Efficiently retrieving a concise set of candidates from a large doc- ument corpus remains a pivotal challenge in Information Retrieval (IR). Neural retrieval models, particularly dense retrieval models built with transformers and pretrained language models, have been popular due to their superior performance. However, criticisms have also been raised on their lack of explainability and vulnerability to adversarial attacks. In response to these challenges, we propose to improve the robustness of dense retrieval models by enhancing their sensitivity of fine-grained relevance signals. A model achieving sensitivity in this context should exhibit high variances when doc- uments' key passages determining their relevance to queries have been modified, while maintaining low variances for other changes in irrelevant passages. This sensitivity allows a dense retrieval model to produce robust results with respect to attacks that try to promote documents without actually increasing their relevance. It also makes it possible to analyze which part of a document is actually relevant to a query, and thus improve the explainability of the retrieval model. Motivated by causality and counterfactual analysis, we propose a se- ries of counterfactual regularization methods based on game theory and unsupervised learning with counterfactual passages. Specifically, we first introduce a cooperative game theory-based counterfactual passage extraction method, identifying the key passages that can influence relevance. Then we propose several subsequent unsuper- vised learning tasks, based on these counterfactual passages, serve to regularize the model's learning process to improve the robustness and sensitivity. Experiments show that, our method can extract key passages without reliance on the passage-level relevance annotations. Moreover, the regularized dense retrieval models exhibit heightened robustness against adversarial attacks, surpassing the state-of-the-art anti-attack methods.

Query rewriting is a fundamental technique in information retrieval (IR). It typically employs the retrieval result as relevance feedback to refine the query and thereby addresses the vocabulary mismatch between user queries and relevant documents. Traditional pseudo-relevance feedback (PRF) and its vector-based extension (VPRF) improve retrieval performance by leveraging top-retrieved documents as relevance feedback. However, they are constructed based on two major hypotheses: the relevance assumption (top documents are relevant) and the model assumption (rewriting methods need to be designed specifically for particular model architectures). While recent large language models (LLMs)-based generative relevance feedback (GRF) enables model-free query reformulation, it either suffers from severe LLM hallucination or, again, relies on the relevance assumption to guarantee the effectiveness of rewriting quality. To overcome these limitations, we introduce an assumption-relaxed framework: Generalized Pseudo Relevance Feedback (GPRF), which performs model-free, natural language rewriting based on retrieved documents, not only eliminating the model assumption but also reducing dependence on the relevance assumption. Specifically, we design a utility-oriented training pipeline with reinforcement learning to ensure robustness against noisy feedback. Extensive experiments across multiple benchmarks and retrievers demonstrate that GPRF consistently outperforms strong baselines, establishing it as an effective and generalizable framework for query rewriting.

Personalized search has been proven to be an effective method to improve ranking quality by tailoring result lists according to the user's search history. Previous studies achieve personalization by learning a user interest profile from the search log, and decide the candidate document's ranking score by calculating its relevance with the learned profile vector. However, existing approaches overlook fine-grained interaction signals by treating the candidate document separately from the user's search history, relying solely on comparisons with a unified interest vector for re-ranking. Leveraging history-document interactions is not trivial due to the challenge of assessing the contributions of fine-grained matching signals within complex evolving interest patterns. In this paper, we address this challenge by helping the model understand these interactions within the evolving interest process through their integration into the interest profiling procedure. Specifically, we hierarchically incorporate these interaction signals as document-aware interests into behavior representations, employing explicit balancing and differentiation mechanisms, while jointly learning the interest pattern from both actual clues derived from original interests and potential insights provided by document-aware interests. Experimental results show that our model obtains substantial improvements over existing methods.

Large Language Models (LLMs) have been proven to have strong zero-shot passage ranking capabilities. In-context learning effectively enhances LLM performance by providing few-shot demonstrations, opening avenues for further improving LLM’s ranking ability. However, existing studies usually retrieve the most similar demonstrations to the input, ignoring the demonstration dependencies and diversity, which is insufficient to inspire the LLM for assessing the current query-passage relevance. In this article, we propose a framework named DemoRank, which selects few-shot demonstrations by performing a novel dependency-aware reranking of the retrieved demonstrations. Considering the dependency, combining top-ranked demonstrations yields better results. Nevertheless, generating the training samples for such a dependency-aware demonstration reranker faces two challenges: (1) the traditional demonstration ranked list assumes demonstration independence, which cannot be used to train our reranker, and (2) obtaining the optimal demonstration ranked list from the retrieved set is NP-hard and inefficient. To overcome these challenges, we propose an approach to construct a kind of dependency-aware training samples efficiently and design a list-pairwise training approach for the optimization of the demonstration reranker. We conduct extensive experiments on a series of passage ranking datasets, and the results demonstrate the superior performance of our proposed DemoRank framework under various scenarios. Our code is publicly available at https://github.com/8421bcd/demorank .

The use of large language models (LLMs) as automated evaluation tools to assess the quality of generated natural language, known as "LLMsas-Judges", has demonstrated promising capabilities and is rapidly gaining widespread attention.However, when applied to pairwise comparisons of candidate responses, LLM-based evaluators often exhibit selection bias.Specifically, their judgments may become inconsistent when the option positions or ID tokens are swapped, compromising the effectiveness and fairness of the evaluation result.To address this challenge, we introduce CalibraEval, a novel label-free method for mitigating selection bias during inference.Specifically, CalibraEval reformulates debiasing as an optimization task aimed at adjusting observed prediction distributions to align with unbiased prediction distributions.To solve this optimization problem, we propose a non-parametric order-preserving algorithm (NOA).This algorithm leverages the partial order relationships between model prediction distributions, thereby eliminating the need for explicit labels and precise mathematical function modeling.Empirical evaluations of LLMs in multiple representative benchmarks demonstrate that Cal-ibraEval effectively mitigates selection bias and improves performance compared to existing debiasing methods.This work marks a step toward building more robust and unbiased automated evaluation frameworks, paving the way for improved reliability in AI-driven assessments.The code can be found at https: //github.com/CSHaitao/CalibraEval.

Large language models (LLMs) exhibit remarkable generative capabilities but often suffer from hallucinations.Retrieval-augmented generation (RAG) offers an effective solution by incorporating external knowledge, but existing methods still face several limitations: additional deployment costs of separate retrievers, redundant input tokens from retrieved text chunks, and the lack of joint optimization of retrieval and generation.To address these issues, we propose RetroLLM, a unified framework that integrates retrieval and generation into a single, auto-regressive process, enabling LLMs to directly generate fine-grained evidence from the corpus with constrained decoding.Moreover, to mitigate false pruning in the process of constrained evidence generation, we introduce (1) hierarchical FM-Index constraints, which generate corpus-constrained clues to identify a subset of relevant documents before evidence generation, reducing irrelevant decoding space; and (2) a forward-looking constrained decoding strategy, which considers the relevance of future sequences to improve evidence accuracy.Extensive experiments on five open-domain QA datasets demonstrate RetroLLM's superior performance across both in-domain and out-ofdomain tasks.The code is available at https: //github.com/sunnynexus/RetroLLM.

Retrieval-augmented Large Language Models (RaLLMs) are reshaping knowledge acquisition, offering long-form, knowledge-grounded answers through advanced reasoning and generation capabilities. Despite the emergence of impactful systems like WebGPT and New Bing, the reliability of RaLLMs, especially in complex situations, is under scrutiny. Our study tackles this concern by evaluating RaLLMs’ question-answering performance using a novel benchmark focusing on Correctness and Groundedness. Correctness measures the logical soundness of the responses, and Groundedness checks for support by relevant references. We introduce an automated model-based evaluation pipeline for multi-hop question-answering tasks, revealing RaLLMs’ proneness to generating inaccuracies when dealing with flawed or partial knowledge. To improve accuracy, we introduce two reasoning strategies, Self-Reflection’ and Self-Completion,’ enabling RaLLMs to identify and fill knowledge gaps, significantly improving answer quality without extensive model retraining.

As Large Language Models (LLMs) demonstrate increasingly strong human-like capabilities, the need to align them with human values has become significant. Recent advanced techniques, such as prompt learning and reinforcement learning, are being employed to bring LLMs closer to aligning with human values. While these techniques address broad ethical and helpfulness concerns, they rarely consider simulating individualized human values. To bridge this gap, we propose SimVBG, a framework that simulates individual values based on individual backstories that reflect their past experience and demographic information. SimVBG transforms structured data on an individual to a backstory and utilizes a multi-module architecture inspired by the Cognitive–Affective Personality System to simulate individual value based on the backstories. We test SimVBG on a self-constructed benchmark derived from the World Values Survey and show that SimVBG improves top-1 accuracy by more than 10% over the retrieval-augmented generation method. Further analysis shows that performance increases as additional interaction user history becomes available, indicating that the model can refine its persona over time. Code, dataset, and complete experimental results are available at https://github.com/bangdedadi/SimVBG.

Large reasoning models (LRMs) like OpenAI-o1 have demonstrated impressive long stepwise reasoning capabilities through large-scale reinforcement learning.However, their extended reasoning processes often suffer from knowledge insufficiency, leading to frequent uncertainties and potential errors.To address this limitation, we introduce Search-o1, a framework that enhances LRMs with an agentic retrievalaugmented generation (RAG) mechanism and a Reason-in-Documents module for refining retrieved documents.Search-o1 integrates an agentic search workflow into the reasoning process, enabling dynamic retrieval of external knowledge when LRMs encounter uncertain knowledge points.Additionally, due to the verbose nature of retrieved documents, we design a separate Reason-in-Documents module to deeply analyze the retrieved information before injecting it into the reasoning chain, minimizing noise and preserving coherent reasoning flow.Extensive experiments on complex reasoning tasks in science, mathematics, and coding, as well as six open-domain QA benchmarks, demonstrate the strong performance of Search-o1.This approach enhances the trustworthiness of LRMs in complex reasoning tasks, paving the way for advanced deep research systems.

Multi-agent techniques such as role playing or multi-turn debates have been shown to be effective in improving the performance of large language models (LLMs) in downstream tasks.Despite their differences in workflows, existing multi-agent systems constructed from a single base LLM mostly use natural language for agent communication.While this is appealing for its simplicity and interpretability, it also introduces inevitable information loss as one model must down sample its continuous state vectors to discrete tokens before transferring them to the other model.Such losses are particularly significant when the information to transfer is not simple facts, but reasoning logics or abstractive thoughts.To tackle this problem, we propose a new communication protocol that transfers both natural language tokens and token-wise state transition trajectory from one agent to another.Particularly, compared to the actual state value, we find that the sequence of state changes in LLMs after generating each token can better reflect the information hidden behind the inference process.We propose a State Delta Encoding (SDE) method to represent state transition trajectories.The experimental results show that multi-agent systems with SDE achieve SOTA performance compared to other communication protocols, particularly in tasks that involve complex reasoning.

Learning from preference feedback is a common practice for aligning large language models (LLMs) with human value. Conventionally, preference data is learned and encoded into a scalar reward model that connects a value head with an LLM to produce a scalar score as preference. However, scalar models lack interpretability and are known to be susceptible to biases in datasets. This paper investigates leveraging LLM itself to learn from such preference data and serve as a judge to address both limitations in one shot. Specifically, we prompt the pre-trained LLM to generate initial judgment pairs with contrastive preference in natural language form. The self-generated contrastive judgment pairs are used to train the LLM-as-a-Judge with Direct Preference Optimization (DPO) and incentivize its reasoning capability as a judge. This proposal of learning the LLMas-a-Judge using self-generated Contrastive judgments (Con-J) ensures natural interpretability through the generated rationales supporting the judgments, and demonstrates higher robustness against bias compared to scalar models. Experimental results show that Con-J outperforms the scalar reward model trained on the same collection of preference data, and outperforms a series of open-source and closed-source generative LLMs. We open-source the training process and model weights of Con-J at https://github.com/YeZiyi1998/Con-J.

Knowledge-intensive tasks often require complex reasoning and contextual understanding over long contexts. However, the learning and deployment of long-LLMs remains a challenging problem despite recent progresses. In this work, we propose that the short LLMs have great potentiality for solving knowledge-intensive tasks that have long context, i.e. they can be solved by purely working with oracle short-contexts within the input long-context. On top of this argument, we propose a framework called DCISO DynamiC knowledge-Intensive task S>Olver), which enables a short-LLM to address the knowledge-intensive tasks with long context via dynamic context browsing. In our framework, the short-LLM prompts itself to reason for two critical decisions: 1) how to access to the appropriate part of context within the input, 2) how to make effective use of the accessed context. By adaptively accessing and utilizing the context based on the presented tasks, DCISO can serve as a general framework to handle diversified knowledge-intensive long-context problems. We comprehensively evaluate different types of tasks from popular long-context benchmarks, where DCISO is able to achieve a substantially improved performance. Our codes will be released at this repository.

The advent of generative artificial intelligence (AI), driven by advancements in large language models (LLMs), has unlocked transformative possibilities for information retrieval (IR), giving rise to a new wave of interactive and conversational paradigms. This workshop, titled New Interaction Paradigms for Information Retrieval in the Era of Generative AI, aims to serve as a collaborative platform for researchers and practitioners to explore the challenges and opportunities of integrating generative AI into IR systems. By focusing on tasks such as multi-turn conversational search, adaptive retrieval interfaces, and context-aware response generation, this workshop will address key areas including system design, user engagement, and evaluation methodologies. The workshop will also delve into broader concerns such as trust, transparency, and fairness, emphasizing the ethical implications of deploying generative AI in IR systems. Through panel discussions, poster sessions, and interactive roundtables, this workshop will foster critical dialogue and innovation, paving the way for a new era of user-centric, generative AI-powered IR systems.

Retrieval-augmented generation (RAG) has emerged as a promising solution to enhance the reliability of large language models (LLMs) with external knowledge. Existing RAG methods share a common strategy for knowledge injection: they place the retrieved documents into the input context of the LLM, which we refer to as the in-context knowledge injection method. While this approach is simple and often effective, it has inherent limitations. Firstly, increasing the context length and number of relevant documents can lead to higher computational overhead and degraded performance, especially in complex reasoning tasks. More importantly, in-context knowledge injection operates primarily at the input level, but LLMs store their internal knowledge in their parameters. This gap fundamentally limits the capacity of in-context methods. To this end, we introduce Parametric RAG, a new RAG paradigm that integrates external knowledge directly into the feed-forward networks of an LLM through document parameterization. This approach not only reduces online computational costs by shortening the input context length, but also deepens the integration of external knowledge by enabling LLMs to utilize it in the same way as internal parametric knowledge. Experimental results demonstrate that Parametric RAG substantially enhances the effectiveness and efficiency of knowledge augmentation in LLMs. Also, it can be combined with in-context RAG methods to achieve even better performance. We have open-sourced all the code, data, and models in the following GitHub link: https://github.com/oneal2000/PRAG

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge retrieved from a knowledge base. However, its effectiveness is fundamentally constrained by the reliability of both the retriever and the knowledge base (i.e., the retrieval system). In real-world scenarios, imperfections in these components often lead to the retrieval of noisy, irrelevant, or misleading counterfactual information, ultimately undermining the trustworthiness of RAG systems. To address this challenge, we propose Robust Fine-Tuning (RbFT), a method designed to enhance the resilience of LLMs against retrieval defects through two targeted fine-tuning tasks. Experimental results demonstrate that RbFT significantly improves the robustness of RAG systems across diverse retrieval conditions, surpassing existing methods while maintaining high inference efficiency and compatibility with other robustness techniques.

Reconstructing visual images from brain signals is a rapidly evolving research with promising applications in brain-computer interfaces, cognitive neuroscience, and assistive technologies. While visual reconstruction based on functional Magnetic Resonance Imaging (fMRI) has previously achieved notable success, this paper explores cost-effective brain signals, i.e., electroencephalography (EEG) and magnetoencephalography (MEG). These signals are less precise than fMRI, which presents greater challenges for reconstruction. To address this problem, we propose BReAD (Brain Image Reconstruction with Retrieval-Augmented Diffusion), a novel framework that combines EEG/MEG signals with retrieval-augmented diffusion models to improve image reconstruction quality. BReAD utilizes the semantics decoded from brain signals for (1) retrieving semantic priors from a large-scale image database and (2) serving as a conditional constraint during the diffusion process. Extensive experiments demonstrate that BReAD significantly outperforms existing approaches in both qualitative and quantitative evaluations, paving the way for more robust and practical brain-to-image reconstruction systems. Our codes are available at https://github.com/Promise-Z5Q2SQ/BReAD.

Information Retrieval (IR) systems are crucial tools for users to access information, which have long been dominated by traditional methods relying on similarity matching. With the advancement of pre-trained language models, Generative Information Retrieval (GenIR) emerges as a novel paradigm, attracting increasing attention. Based on the form of information provided to users, current research in GenIR can be categorized into two aspects: (1) Generative Retrieval ( GR ) leverages the generative model’s parameters for memorizing documents, enabling retrieval by directly generating relevant document identifiers without explicit indexing. (2) Reliable Response Generation employs language models to directly generate information users seek, breaking the limitations of traditional IR in terms of document granularity and relevance matching while offering flexibility, efficiency, and creativity to meet practical needs. This article aims to systematically review the latest research progress in GenIR. We will summarize the advancements in GR regarding model training and structure, document identifier, incremental learning, and so on, as well as progress in reliable response generation in aspects of internal knowledge memorization, external knowledge augmentation, and so on. We also review the evaluation, challenges, and future developments in GenIR systems. This review aims to offer a comprehensive reference for researchers, encouraging further development in the GenIR field (Github Repository: https://github.com/RUC-NLPIR/GenIR-Survey ).

Generative information retrieval, encompassing two major tasks of Generative Document Retrieval (GDR) and Grounded Answer Generation (GAR), has gained significant attention in natural language processing. Existing methods for GDR and GAR rely on separate retrieval and reader modules, which hinder simultaneous optimization. To overcome this, we present UniGen, a Unified Generative framework for retrieval and question answering that integrates both tasks into a single generative model leveraging the capabilities of large language models. UniGen employs a shared encoder and two distinct decoders for generative retrieval and question answering. To facilitate the learning of both tasks, we introduce connectors, generated by large language models, to bridge the gaps between query inputs and generation targets, as well as between document identifiers and answers. Furthermore, we propose an iterative enhancement strategy that leverages generated answers and retrieved documents to iteratively improve both tasks. Through extensive experiments on the MS MARCO and NQ datasets, we demonstrate the effectiveness of UniGen, showcasing its superior performance in both retrieval and question answering tasks.

This paper presents a novel Chunking-Free In-Context (CFIC) retrieval approach, specifically tailored for Retrieval-Augmented Generation (RAG) systems.Traditional RAG systems often struggle with grounding responses using precise evidence text due to the challenges of processing lengthy documents and filtering out irrelevant content.Commonly employed solutions, such as document chunking and adapting language models to handle longer contexts, have their limitations.These methods either disrupt the semantic coherence of the text or fail to effectively address the issues of noise and inaccuracy in evidence retrieval.CFIC addresses these challenges by circumventing the conventional chunking process.It utilizes the encoded hidden states of documents for in-context retrieval, employing autoaggressive decoding to accurately identify the specific evidence text required for user queries, eliminating the need for chunking.CFIC is further enhanced by incorporating two decoding strategies, namely Constrained Sentence Prefix Decoding and Skip Decoding.These strategies not only improve the efficiency of the retrieval process but also ensure that the fidelity of the generated grounding text evidence is maintained.Our evaluations of CFIC on a range of open QA datasets demonstrate its superiority in retrieving relevant and accurate evidence, offering a significant improvement over traditional methods.By doing away with the need for document chunking, CFIC presents a more streamlined, effective, and efficient retrieval solution, making it a valuable advancement in the field of RAG systems.The codes will be released in this repository.

Generating clarifying questions can effectively clarify users' complicated search intent in conversational search systems. However, existing methods based on pre-defined templates are inadequate in understanding explicit user intents, making generated questions monotonous or inaccurate in some cases. In this paper, we define the ''intent'' of a query as a verb representing the potential behavior, action, or task the user may take. We study generating clarifying questions from a new perspective by incorporating the intents explicitly to form ''intent-aware'' questions with high informativeness and accuracy. Since obtaining gold intent-aware questions is expensive, we propose a rule-based method and a continual learning model to generate intent-aware questions as weak supervision signals. The former leverages search results to mine contextual intent-aware words or phrases, and the latter relies on parallel corpora to paraphrase template-based questions by incorporating the intents. The generated weak supervision data are then applied to fine-tune a BART-based model for end-to-end intent-aware question generation. We also explore to prompt a large language model to generate intent-aware questions. Experimental results on a public clarification dataset demonstrate that our proposed methods improve users' search experience compared to existing methods.

The emergence of Large Language Models (LLMs) has significantly advanced natural language processing, but these models often generate factually incorrect information, known as "hallucination." Initial retrieval-augmented generation (RAG) methods like the "Retrieve-Read" framework was inadequate for complex reasoning tasks. Subsequent prompt-based RAG strategies and Supervised Fine-Tuning (SFT) methods improved performance but required frequent retraining and risked altering foundational LLM capabilities. To cope with these challenges, we propose Assistant-based Retrieval-Augmented Generation (AssistRAG), integrating an intelligent information assistant within LLMs. This assistant manages memory and knowledge through tool usage, action execution, memory building, and plan specification. Using a two-phase training approach—Curriculum Assistant Learning and Reinforced Preference Optimization—AssistRAG enhances information retrieval and decision-making. Experiments show AssistRAG significantly outperforms benchmarks, especially benefiting less advanced LLMs, by providing superior reasoning capabilities and accurate responses.

Large language models (LLMs) have gained significant attention in various fields but prone to hallucination, especially in knowledge-intensive (KI) tasks. To address this, retrieval-augmented generation (RAG) has emerged as a popular solution to enhance factual accuracy. However, traditional retrieval modules often rely on large document index and disconnect with generative tasks. With the advent of generative retrieval (GR), language models can retrieve by directly generating document identifiers (DocIDs), offering superior performance in retrieval tasks. However, the potential relationship between GR and downstream tasks remains unexplored. In this paper, we propose CorpusLM, a unified language model that leverages external corpus to tackle various knowledge-intensive tasks by integrating generative retrieval, closed-book generation, and RAG through a unified greedy decoding process. We design the following mechanisms to facilitate effective retrieval and generation, and improve the end-to-end effectiveness of KI tasks: (1) We develop a ranking-oriented DocID list generation strategy, which refines GR by directly learning from a DocID ranking list, to improve retrieval quality. (2) We design a continuous DocIDs-References-Answer generation strategy, which facilitates effective and efficient RAG. (3) We employ well-designed unsupervised DocID understanding tasks, to comprehend DocID semantics and their relevance to downstream tasks. We evaluate our approach on the widely used KILT benchmark with two variants of backbone models, i.e., T5 and Llama2. Experimental results demonstrate the superior performance of our models in both retrieval and downstream tasks.

Recently, generative retrieval has emerged as a promising alternative to the traditional retrieval paradigms. It assigns each document a unique identifier, known as the DocID, and employs a generative model to directly generate the relevant DocID for the input query. A common choice for the DocID is one or several natural language sequences, e.g. the title, synthetic queries, or n-grams, so that the pre-trained knowledge of the generative model can be effectively utilized. However, a sequence is generated token by token, where only the most likely candidates are kept and the rest are pruned at each decoding step, thus, retrieval fails if any token within the relevant DocID is falsely pruned. What's worse, during decoding, the model can only perceive preceding tokens in the DocID while being blind to subsequent ones, hence is prone to make such errors. To address this problem, we present a novel framework for generative retrieval, dubbed Term-Set Generation (TSGen). Instead of sequences, we use a set of terms as the DocID. The terms are selected based on learned weights from relevance signals, so that they concisely summarize the document's semantics and distinguish it from others. On top of the term-set DocID, we propose a permutation-invariant decoding algorithm, with which the term set can be generated in any permutation yet will always lead to the corresponding document. Remarkably, TSGen perceives all valid terms rather than only the preceding ones at each decoding step. Given the constant decoding space, it can make more reliable decisions due to the broader perspective. TSGen is also resilient to errors: the relevant DocID will not be falsely pruned as long as the decoded term belongs to it. Moreover, TSGen can explore the optimal decoding permutation of the term set on its own, which further improves the likelihood of generating the relevant DocID. Lastly, we design an iterative optimization procedure to incentivize the model to generate the relevant term set in its favorable permutation. We conduct extensive experiments on popular benchmarks of generative retrieval, which validate the effectiveness, the generalizability, the scalability, and the efficiency of TSGen.

Retrieval-augmented generation have become central in natural language processing due to their efficacy in generating factual content. While traditional methods employ single-time retrieval, more recent approaches have shifted towards multi-time retrieval for multi-hop reasoning tasks. However, these strategies are bound by predefined reasoning steps, potentially leading to inaccuracies in response generation. This paper introduces MetaRAG, an approach that combines the retrieval-augmented generation process with metacognition. Drawing from cognitive psychology, metacognition allows an entity to self-reflect and critically evaluate its cognitive processes. By integrating this, MetaRAG enables the model to monitor, evaluate, and plan its response strategies, enhancing its introspective reasoning abilities. Through a three-step metacognitive regulation pipeline, the model can identify inadequacies in initial cognitive responses and fixes them. Empirical evaluations show that MetaRAG significantly outperforms existing methods.

Traditional search engines usually provide identical search results for all users, overlooking individual preferences. To counter this limitation, personalized search has been developed to re-rank results based on user preferences derived from query logs. Deep learning-based personalized search methods have shown promise, but they rely heavily on abundant training data, making them susceptible to data sparsity challenges. This paper proposes a Cognitive Personalized Search (CoPS) model, which integrates Large Language Models (LLMs) with a cognitive memory mechanism inspired by human cognition. CoPS employs LLMs to enhance user modeling and user search experience. The cognitive memory mechanism comprises sensory memory for quick sensory responses, working memory for sophisticated cognitive responses, and long-term memory for storing historical interactions. CoPS handles new queries using a three-step approach: identifying re-finding behaviors, constructing user profiles with relevant historical information, and ranking documents based on personalized query intent. Experiments show that CoPS outperforms baseline models in zero-shot scenarios.

Document retrieval has been extensively studied within theindex-retrieveframework for decades, which has withstood the test of time. However, this approach inherently segregates the indexing and retrieval processes, preventing a cohesive, end-to-end optimization. To bridge this divide, we introduce WebUltron, a revolutionary model-centric indexer for document retrieval. This system embeds the entirety of document knowledge within the model, striving for seamless end-to-end retrieval. Two primary challenges with this indexer are the representation of document identifiers (docids) and the model's training. Current methods grapple with docids that lack semantic depth and the constraints of limited supervised data, making scaling up to larger datasets challenging. Addressing this, we've engineered two novel docid types imbued with richer semantics that also streamline model inference. Further enhancing WebUltron's capabilities, we've developed a three-stage training regimen, leveraging deeper corpus insights and fortifying query-docid relationships. Experiments on two public datasets demonstrate the superiority of WebUltron over advanced baselines for document retrieval.

Given a user, a personalized search model relies on her historical behaviors, such as issued queries and their clicked documents, to generate an interest profile and personalize search results accordingly. In interest profiling, most existing personalized search approaches use “static” document representations as the inputs, which do not change with the current search. However, a document is usually long and contains multiple pieces of information, a static fix-length document vector is usually insufficient to represent the important information related to the original query or the current query, and makes the profile noisy and ambiguous. To tackle this problem, we propose building dynamic and intent-oriented document representations which highlight important parts of a document rather than simply encode the entire text. Specifically, we divide each document into multiple passages, and then separately use the original query and the current query to interact with the passages. Thereafter we generate two “dynamic” document representations containing the key information around the historical and the current user intent, respectively. We then profile interest by capturing the interactions between these document representations, the historical queries, and the current query. Experimental results on a real-world search log dataset demonstrate that our model significantly outperforms state-of-the-art personalization methods.

In recent years, various dense retrieval methods have been developed to improve the performance of search engines with a vectorized index. However, these approaches require a large pre-computed index and have a limited capacity to memorize all semantics in a document within a single vector. To address these issues, researchers have explored end-to-end generative retrieval models that use a seq-to-seq generative model to directly return identifiers of relevant documents. Although these models have been effective, they are often trained with the MLE method. It only encourages the model to assign a high probability to the relevant document identifier, ignoring the relevance comparisons of other documents. This may lead to performance degradation in ranking tasks, where the core is to compare the relevance between documents. To address this issue, we propose a ranking-oriented generative retrieval model that incorporates relevance signals to better estimate the relative relevance of different documents in ranking tasks. Based upon the analysis of the optimization objectives of dense retrieval and generative retrieval, we propose utilizing dense retrieval to provide relevance feedback for generative retrieval. Under an alternate training framework, the generative retrieval model gradually acquires higher-quality ranking signals to optimize the model. Experimental results show that our approach increasing Recall@1 by 12.9% with respect to the baselines on MS MARCO dataset.

Model-based Information Retrieval (Model-based IR) has gained attention due to advancements in generative language models. Unlike traditional dense retrieval methods relying on dense vector representations of documents, model-based IR leverages language models to retrieve documents by generating their unique discrete identifiers (docids). This approach effectively reduces the requirements to store separate document representations in an index. Most existing model-based IR approaches utilize pre-defined static docids, i.e., these docids are fixed and are not learnable by training on the retrieval tasks. However, these docids are not specifically optimized for retrieval tasks, which makes it difficult to learn semantics and relationships between documents and achieve satisfactory retrieval performance. To address the above limitations, we propose Neural Optimized VOcabularial (NOVO) docids. NOVO docids are unique n-gram sets identifying each document. They can be generated in any order to retrieve the corresponding document and can be optimized through training to better learn semantics and relationships between documents. We propose to optimize NOVO docids through query denoising modeling and retrieval tasks, allowing for optimizing both semantic and token representations for such docids. Experiments on two datasets under the normal and zero-shot settings show that NOVO exhibits strong performance in more effective and interpretable model-based IR.

Document retrieval has always been a crucial problem in Web search. Recent works leverage pre-trained language models to represent documents in dense vectors. However, these works focus on the textual content but ignore the appearance of web pages (e.g., the visual style, the layout, and the images), which are actually essential for information delivery. To alleviate this problem, we propose a new dense retrieval model, namely VILE, to incorporate visual features into document representations. However, because a web page is usually very large and contains diverse information, simply concatenating its textual and visual features may result in a cluttered multi-modal representation that lacks focus on the important parts of the page. We observe that web pages often have a structured content organization, comprising multiple blocks that convey different information. Motivated by the observation, we propose building a multi-modal document representation by aggregating the fine-grained multi-modal block representations, to enable a more comprehensive understanding of the page. Specifically, we first segment a web page into multiple blocks, then create multi-modal features for each block. %allowing for more effective capture of its content and visual information. The representations of all blocks are then integrated into the final multi-modal page representation. VILE can better model the importance of different content regions, leading to a high-quality multi-modal representation. We collect screenshots and the corresponding layout information of some web pages in the MS MARCO Document Ranking dataset, resulting in a new multi-modal document retrieval dataset. Experimental results conducted on this dataset demonstrate that our model exhibits significant improvements over existing document retrieval models. Our code is available at https://github.com/yhy-2000/VILE.

The recent advent of end-to-end generative retrieval marks a significant shift in document retrieval methods, leveraging differentiable search indexes to directly produce relevant document identifiers (docids) in response to a specific query.Nevertheless, this approach faces two fundamental challenges: (i) a discrepancy between the token-level probabilistic optimization and the broader document-level relevance estimation; (ii) an overemphasis on top-1 results at the expense of overall ranking quality.To tackle these challenges, we propose a generative retrieval model with reinforcement learning from relevance feedback, which aims to align token-level docid generation with document-level relevance estimation.The training process incorporates three stages: supervised fine-tuning, relevance reward model training, and reinforced learning-to-rank from relevance feedback.To train a high-quality reward model, we define "relevance" under three progressive scenarios, which collectively offer a comprehensive evaluation of the document relevance.Experiments conducted on two benchmark datasets demonstrate the effectiveness of our proposed approach.

Recently, pretrained models have achieved remarkable performance not only in natural language processing but also in information retrieval (IR). Previous studies show that IR-oriented pretraining tasks can achieve better performance than only finetuning pretrained language models in IR datasets. Besides, the massive search log data obtained from mainstream search engines can be used in IR pretraining, for it contains users' implicit judgments of document relevance under a concrete query. However, existing methods mainly use direct query-document click signals to pretrain models. The potential supervision signals from search logs are far from being well explored. In this paper, we propose to comprehensively leverage four query-document relevance relations, including co-interaction and multi-hop relations, to pretrain ranking models in IR. Specifically, we focus on the user's click behavior and construct an Interaction Graph to represent the global relevance relations between queries and documents from all search logs. With the graph, we can consider the co-interaction and multi-hop q-d relationships through their neighbor nodes. Based on the relations extracted from the interaction graph, we propose four strategies to generate contrastive positive and negative q-d pairs and use these data to pretrain ranking models. Experimental results on both industrial and academic datasets demonstrate the effectiveness of our method.

The key to personalized search is modeling user intents to tailor returned results for different users. Existing personalized methods mainly focus on learning implicit user interest vectors. In this paper, we propose ExpliPS, a personalized search model that explicitly incorporates query subtopics into personalization. It models the user’s current intent by estimating the user’s preference over the subtopics of the current query and personalizes the results over the weighted subtopics. We think that in such a way, personalized search could be more explainable and stable. Specifically, we first employ a semantic encoder to learn the representations of the user’s historical behaviours. Then with the historical behaviour representations, a subtopic preference encoder is devised to predict the user’s subtopic preferences on the current query. Finally, we rerank the candidates via a subtopic-aware ranker that prioritizes the documents relevant to the user-preferred subtopics. Experimental results show our model ExpliPS outperforms the state-of-the-art personalized web search models with explainable and stable results.

The goal of personalized search is to tailor the document ranking list to meet user's individual needs. Previous studies showed users usually look for the information that has been searched before. This is called re-finding behavior which is widely explored in existing personalized search approaches. However, most existing methods for identifying re-finding behavior focus on simple lexical similarities between queries. In this paper, we propose a personalized framework based on hierarchical memory networks (MN) to enhance the identification of the potential re-finding behavior. Specifically, we explore the potential re-finding behaviors of users from two dimensions. (1) Granularity dimension. The framework carries out re-finding identification with external memories from word, sentence, and session levels. (2) Query intent dimension. Query-based re-finding and document-based re-finding are taken into account to cover user's different query intents. To enhance the interaction between different memory slots, we optimize the$READ$operation of MN with two strategies that utilize the information in memory in a multi-hop way. Endowed with these memory networks, we can enhance user's potential re-finding behaviors and build a fine-grained user model dynamically. Experimental results on two datasets have a significant improvement over baselines, and the optimized$READ$operation shows better performance.

Personalized search improves the quality of search results by modeling historical user behavior. In recent years, many methods based on deep learning have greatly improved the performance of personalized search. However, most of the existing methods only focus on modeling positive user behavior signals, which leads to incomplete user interest modeling. At the same time, the user's search behavior hides much explicit or implicit feedback information. For example, clicking and staying for a certain period represents implicit positive feedback, and skipping behavior represents implicit negative feedback. Intuitively, this information can be utilized to construct a more complete and accurate user profile. In this paper, we propose a dual-feedback modeling framework, which integrates multi-granular user feedback information to model the user's current search intention. Specifically, we propose a feedback extraction network to refine the dual-feedback representation in multiple stages. For enhancing the user's real-time search quality, we design an additional dual-feedback feature gating module to capture the user's real-time feedback in the current session. We conducted a large number of experiments on two real-world datasets, and the experimental results show that our method can effectively improve the performance of personalized search.

Utilizing pre-trained language models has achieved great success for neural document ranking. Limited by the computational and memory requirements, long document modeling becomes a critical issue. Recent works propose to modify the full attention matrix in Transformer by designing sparse attention patterns. However, most of them only focus on local connections of terms within a fixed-size window. How to build suitable remote connections between terms to better model document representation remains underexplored. In this paper, we propose the model Socialformer, which introduces the characteristics of social networks into designing sparse attention patterns for long document modeling in document ranking. Specifically, we consider several attention patterns to construct a graph like social networks. Endowed with the characteristic of social networks, most pairs of nodes in such a graph can reach with a short path while ensuring the sparsity. To facilitate efficient calculation, we segment the graph into multiple subgraphs to simulate friend circles in social scenarios. Experimental results confirm the effectiveness of our model on long document modeling.

Personalized search plays a crucial role in improving user search experience owing to its ability to build user profiles based on historical behaviors. Previous studies have made great progress in extracting personal signals from the query log and learning user representations. However, neural personalized search is extremely dependent on sufficient data to train the user model. Data sparsity is an inevitable challenge for existing methods to learn high-quality user representations. Moreover, the overemphasis on final ranking quality leads to rough data representations and impairs the generalizability of the model. To tackle these issues, we propose a Personalized Search framework with Self-supervised Learning (PSSL) to enhance data representations. Specifically, we adopt a contrastive sampling method to extract paired self-supervised information from sequences of user behaviors in query logs. Four auxiliary tasks are designed to pre-train the sentence encoder and the sequence encoder used in the ranking model. They are optimized by contrastive loss which aims to close the distance between similar user sequences, queries, and documents. Experimental results on two datasets demonstrate that our proposed model PSSL achieves state-of-the-art performance compared with existing baselines.

The key to personalized search is to build the user profile based on historical behaviour. To deal with the users who lack historical data, group based personalized models were proposed to incorporate the profiles of similar users when re-ranking the results. However, similar users are mostly found based on simple lexical or topical similarity in search behaviours. In this paper, we propose a neural network enhanced method to highlight similar users in semantic space. Furthermore, we argue that the behaviour-based similar users are still insufficient to understand a new query when user's historical activities are limited. To tackle this issue, we introduce the friend network into personalized search to determine the closeness between users in another way. Since the friendship is often formed based on similar background or interest, there are plenty of personalized signals hidden in the friend network naturally. Specifically, we propose a friend network enhanced personalized search model, which groups the user into multiple friend circles based on search behaviours and friend relations respectively. These two types of friend circles are complementary to construct a more comprehensive group profile for refining the personalization. Experimental results show the significant improvement of our model over existing personalized search models.

The key to personalized search is to clarify the meaning of current query based on user's search history. Previous personalized studies tried to build user profiles on the basis of historical data to tailor the ranking. However, we argue that the user profile based methods do not really disambiguate the current query. They still retain some semantic bias when building user profiles. In this paper, we propose to encode history with context-aware representation learning to enhance the representation of current query, which is a direct way to clarify the user's information need. Specifically, endowed with the benefit from transformer on aggregating contextual information, we devise a query disambiguation model to parse the meaning of current query in multiple stages. Moreover, for covering the cases that current query is not sufficient to express the intent, we train a personalized language model to predict user intent from existing queries. Under the interaction of two sub-models, we can generate the context-aware representation of current query and re-rank the results based on it. Experimental results show the significant improvement of our model compared with previous methods.

The goal of personalized search is to tailor the document ranking list to meet user's individual needs. Previous studies showed users usually look for the information that has been searched before. This is called re-finding behavior which is widely explored in existing personalized search approaches. However, most existing methods for identifying re-finding behavior focus on simple lexical similarities between queries. In this paper, we propose to construct memory networks (MN) to support the identification of more complex re-finding behavior. Specifically, incorporating semantic information, we devise two external memories to make an expansion of re-finding based on the query and the document respectively. We further design an intent memory to recognize session-based re-finding behavior. Endowed with these memory networks, we can build a fine-grained user model dynamically based on the current query and documents, and use the model to re-rank the results. Experimental results show the significant improvement of our model compared with traditional methods.