Trial-and-error is a fundamental strategy for humans to solve complex problems and a necessary capability for Artificial Intelligence (AI) systems operating in real-world environments. Although several trial-and-error AI techniques have recently been proposed, most of them rely on simple heuristics designed by researchers and achieve limited performance gains. The core issue is the absence of appropriate data: current models cannot learn from detailed records of how humans actually conduct trial-and-error in practice. To address this gap, we introduce a data annotation platform and a corresponding dataset, termed Trial-and-Error Collection (TEC). The platform records users' complete trajectories across multiple trials and collects their reflections after receiving error feedback. Using this platform, we record the problem-solving processes of 46 participants on 58 tasks, resulting in 5,370 trial trajectories along with error reflections across 41,229 webpages. With this dataset, we observe that humans achieve substantially higher accuracy compared to LLMs, which demonstrates that humans are more effective in trial-and-error than LLMs. We believe that the TEC platform and dataset provide a valuable foundation for understanding human trial-and-error behavior and for developing more capable AI systems. Platform and dataset are publicly available. https://github.com/Serendipity0429/TEC.

Retrieval-Augmented Generation (RAG) has become a foundational paradigm for enhancing large language models (LLMs) with external knowledge, playing an important role in modern information retrieval and knowledge-intensive NLP applications. Standard RAG systems typically adopt a static retrieve-then-generate pipeline and rely on in-context knowledge injection, which can be suboptimal for complex tasks that require multihop reasoning, adaptive information access, and deeper integration of external knowledge. Motivated by these limitations, the research community has moved beyond static retrieval and in-context knowledge injection. Among the emerging directions, this tutorial delves into two rapidly growing and complementary research directions on RAG: Dynamic RAG and Parametric RAG. Dynamic RAG explores how LLMs can actively decide when and what to retrieve during generation, enabling real-time adaptation to evolving information needs. Parametric RAG rethinks how the retrieved knowledge should be incorporated, moving from input-level to parameter-level knowledge injection for improved efficiency and effectiveness. This tutorial offers a comprehensive overview of recent advances in both directions. It provides participants with the theoretical foundations and actionable insights needed to build flexible and scalable RAG systems.

Scaling laws have been observed in a wide range of tasks, particularly in language generation. Previous studies have found that the performance of large language models adheres to predictable patterns with respect to the size of models and datasets. This helps us design training strategies effectively and efficiently, especially as large-scale training becomes increasingly resource-intensive. Yet, in dense retrieval, such scaling law has not been fully explored. In this study, we investigate how scaling affects the performance of dense retrieval models. We implement dense retrieval models with different numbers of parameters, and train them with various amounts of annotated data. We propose to use the contrastive entropy as the evaluation metric, which is continuous compared with discrete ranking metrics and thus can accurately reflect model performance. Results indicate that the performance of dense retrieval models follows a precise power-law scaling related to the model size and the number of annotations across different datasets and annotation methods. Additionally, we show that the scaling laws help optimize the training process, such as resolving the resource allocation problem under a budget constraint. We believe that these findings significantly contribute to understanding the scaling effect of dense retrieval models and offer meaningful guidance for future research.

Text-to-image generation systems have emerged as revolutionary tools in the realm of artistic creation, offering unprecedented ease in transforming textual prompts into visual art. However, the efficacy of these systems is intricately linked to the quality of user-provided prompts, which often poses a challenge to users unfamiliar with prompt crafting. This paper addresses this challenge by leveraging user reformulation data from interaction logs to develop an automatic prompt reformulation model. Our in-depth analysis of these logs reveals that user prompt reformulation is heavily dependent on the individual user's capability, resulting in significant variance in the quality of reformulation pairs. To effectively use this data for training, we introduce the Capability-aware Prompt Reformulation (CAPR) framework. CAPR innovatively integrates user capability into the reformulation process through two key components: the Conditional Reformulation Model (CRM) and Configurable Capability Features (CCF). CRM reformulates prompts according to a specified user capability, as represented by CCF. The CCF, in turn, offers the flexibility to tune and guide the CRM's behavior. This enables CAPR to effectively learn diverse reformulation strategies across various user capacities and to simulate high-capability user reformulation during inference. Extensive experiments demonstrate CAPR's superior performance over existing baselines and its remarkable robustness on unseen systems. Furthermore, comprehensive analyses validate the effectiveness of different components. CAPR can facilitate user-friendly interaction with text-to-image systems and make advanced artistic creation more achievable for a broader range of users.

Recent studies have shown that Dense Retrieval (DR) techniques can significantly improve the performance of first-stage retrieval in IR systems. Despite its empirical effectiveness, the application of DR is still limited. In contrast to statistic retrieval models that rely on highly efficient inverted index solutions, DR models build dense embeddings that are difficult to be pre-processed with most existing search indexing systems. To avoid the expensive cost of brute-force search, the Approximate Nearest Neighbor (ANN) algorithm and corresponding indexes are widely applied to speed up the inference process of DR models. Unfortunately, while ANN can improve the efficiency of DR models, it usually comes with a significant price on retrieval performance.

A retrieval model should not only interpolate the training data but also extrapolate well to the queries that are different from the training data. While neural retrieval models have demonstrated impressive performance on ad-hoc search benchmarks, we still know little about how they perform in terms of interpolation and extrapolation. In this paper, we demonstrate the importance of separately evaluating the two capabilities of neural retrieval models. Firstly, we examine existing ad-hoc search benchmarks from the two perspectives. We investigate the distribution of training and test data and find a considerable overlap in query entities, query intent, and relevance labels. This finding implies that the evaluation on these test sets is biased toward interpolation and cannot accurately reflect the extrapolation capacity. Secondly, we propose a novel evaluation protocol to separately evaluate the interpolation and extrapolation performance on existing benchmark datasets. It resamples the training and test data based on query similarity and utilizes the resampled dataset for training and evaluation. Finally, we leverage the proposed evaluation protocol to comprehensively revisit a number of widely-adopted neural retrieval models. Results show models perform differently when moving from interpolation to extrapolation. For example, representation-based retrieval models perform almost as well as interaction-based retrieval models in terms of interpolation but not extrapolation. Therefore, it is necessary to separately evaluate both interpolation and extrapolation performance and the proposed resampling method serves as a simple yet effective evaluation tool for future IR studies.

Dense Retrieval (DR) has achieved state-of-the-art first-stage ranking effectiveness. However, the efficiency of most existing DR models is limited by the large memory cost of storing dense vectors and the time-consuming nearest neighbor search (NNS) in vector space. Therefore, we present RepCONC, a novel retrieval model that learns discrete Representations via CONstrained Clustering. RepCONC jointly trains dual-encoders and the Product Quantization (PQ) method to learn discrete document representations and enables fast approximate NNS with compact indexes. It models quantization as a constrained clustering process, which requires the document embeddings to be uniformly clustered around the quantization centroids and supports end-to-end optimization of the quantization method and dual-encoders. We theoretically demonstrate the importance of the uniform clustering constraint in RepCONC and derive an efficient approximate solution for constrained clustering by reducing it to an instance of the optimal transport problem. Besides constrained clustering, RepCONC further adopts a vector-based inverted file system (IVF) to support highly efficient vector search on CPUs. Extensive experiments on two popular ad-hoc retrieval benchmarks show that RepCONC achieves better ranking effectiveness than competitive vector quantization baselines under different compression ratio settings. It also substantially outperforms a wide range of existing retrieval models in terms of retrieval effectiveness, memory efficiency, and time efficiency.

Recently, Information Retrieval community has witnessed fast-paced advances in Dense Retrieval (DR), which performs first-stage retrieval with embedding-based search. Despite the impressive ranking performance, previous studies usually adopt brute-force search to acquire candidates, which is prohibitive in practical Web search scenarios due to its tremendous memory usage and time cost. To overcome these problems, vector compression methods have been adopted in many practical embedding-based retrieval applications. One of the most popular methods is Product Quantization (PQ). However, although existing vector compression methods including PQ can help improve the efficiency of DR, they incur severely decayed retrieval performance due to the separation between encoding and compression. To tackle this problem, we present JPQ, which stands for Joint optimization of query encoding and Product Quantization. It trains the query encoder and PQ index jointly in an end-to-end manner based on three optimization strategies, namely ranking-oriented loss, PQ centroid optimization, and end-to-end negative sampling. We evaluate JPQ on two publicly available retrieval benchmarks. Experimental results show that JPQ significantly outperforms popular vector compression methods. Compared with previous DR models that use brute-force search, JPQ almost matches the best retrieval performance with 30x compression on index size. The compressed index further brings 10x speedup on CPU and 2x speedup on GPU in query latency.

Ranking has always been one of the top concerns in information retrieval researches. For decades, the lexical matching signal has dominated the ad-hoc retrieval process, but solely using this signal in retrieval may cause the vocabulary mismatch problem. In recent years, with the development of representation learning techniques, many researchers turn to Dense Retrieval (DR) models for better ranking performance. Although several existing DR models have already obtained promising results, their performance improvement heavily relies on the sampling of training examples. Many effective sampling strategies are not efficient enough for practical usage, and for most of them, there still lacks theoretical analysis in how and why performance improvement happens. To shed light on these research questions, we theoretically investigate different training strategies for DR models and try to explain why hard negative sampling performs better than random sampling. Through the analysis, we also find that there are many potential risks in static hard negative sampling, which is employed by many existing training methods. Therefore, we propose two training strategies named a Stable Training Algorithm for dense Retrieval (STAR) and a query-side training Algorithm for Directly Optimizing Ranking pErformance (ADORE), respectively. STAR improves the stability of DR training process by introducing random negatives. ADORE replaces the widely-adopted static hard negative sampling method with a dynamic one to directly optimize the ranking performance. Experimental results on two publicly available retrieval benchmark datasets show that either strategy gains significant improvements over existing competitive baselines and a combination of them leads to the best performance.

Although BERT has shown its effectiveness in a number of IR-related tasks, especially document ranking, the understanding of its internal mechanism remains insufficient. To increase the explainability of the ranking process performed by BERT, we investigate a state-of-the-art BERT-based ranking model with focus on its attention mechanism and interaction behavior. Firstly, we look into the evolving of the attention distribution. It shows that in each step, BERT dumps redundant attention weights on tokens with high document frequency (such as periods). This may lead to a potential threat to the model robustness and should be considered in future studies. Secondly, we study how BERT models interactions between query and document and find that BERT aggregates document information to query token representations through their interactions, but extracts query-independent representations for document tokens. It indicates that it is possible to transform BERT into a more efficient representation-focused model. These findings help us better understand the ranking process by BERT and may inspire future improvement.

Document ranking is one of the most studied but challenging problems in information retrieval (IR) research. A number of existing document ranking models capture relevance signals at the whole document level. Recently, more and more research has begun to address this problem from fine-grained document modeling. Several works leveraged fine-grained passage-level relevance signals in ranking models. However, most of these works focus on context-independent passage-level relevance signals and ignore the context information, which may lead to inaccurate estimation of passage-level relevance. In this paper, we investigate how information gain accumulates with passages when users sequentially read a document. We propose the context-aware Passage-level Cumulative Gain (PCG), which aggregates relevance scores of passages and avoids the need to formally split a document into independent passages. Next, we incorporate the patterns of PCG into a BERT-based sequential model called Passage-level Cumulative Gain Model (PCGM) to predict the PCG sequence. Finally, we apply PCGM to the document ranking task. Experimental results on two public ad hoc retrieval benchmark datasets show that PCGM outperforms most existing ranking models and also indicates the effectiveness of PCG signals. We believe that this work contributes to improving ranking performance and providing more explainability for document ranking.