Conversational search aims to satisfy users’ complex information needs via multiple-turn interactions. The key challenge lies in revealing real users’ search intent from the context-dependent queries. Previous studies achieve conversational search by fine-tuning a conversational dense retriever with relevance judgments between pairs of context-dependent queries and documents. However, this training paradigm encounters data scarcity issues. To this end, we propose ConvMix, a mixed-criteria framework to augment conversational dense retrieval, which covers more aspects than existing data augmentation frameworks. We design a two-sided relevance judgment augmentation schema in a scalable manner via the aid of large language models. Besides, we integrate the framework with quality control mechanisms to obtain semantically diverse samples and near-distribution supervisions to combine various annotated data. Experimental results on five widely used benchmarks show that the conversational dense retriever trained by our ConvMix framework outperforms previous baseline methods, which demonstrates our superior effectiveness.

Heterogeneous Graph Neural Networks (HGNNs) have demonstrated remarkable capabilities in capturing effective information in heterogeneous graphs, achieving outstanding performance in various learning tasks. However, the heavy dependency of HGNNs on neighbors information may result in high latency, which restricts their practicality in real-world applications. Recent studies have attempted to overcome such latency in Graph Neural Networks (GNNs) by distilling knowledge into student models that do not rely on graph structure. But these approaches primarily focus on replicating teachers' predictive outcomes while neglecting the structural knowledge they encoded. This limitation makes such approach less effective when graphs become complex, particularly on heterogeneous graphs. Motivated by this challenge, we propose HGKD, a novel hierarchical knowledge distillation framework that transfers both structural knowledge and predictive outcomes from HGNN teachers to a multi-layer perceptron student. Additionally, we provide two variants of HGKD that help the student learn from multiple teacher models through Pareto learning and incorporate low-cost neighbor information. We evaluate HGKD and its variants on a range of heterogeneous graph datasets. The results demonstrate that our student model achieves performance comparable to or exceeding that of HGNN teachers, despite not relying on graph structures during inference.

Jiongxiao Wang, Qiaojing Yan, Yawei Wang, Yijun Tian, Soumya Smruti Mishra, Zhichao Xu, Megha Gandhi, Panpan Xu, Lin Lee Cheong. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Large language models increasingly serve as judges in AI evaluation, but current approaches rely on consensus preferences that ignore individual evaluator variation. We propose a novel simulation approach that combines categorical judgments with evaluator-specific auxiliary data—retrospective reasoning traces and interface telemetry—to enable LLM-based simulation of individual evaluators via in-context learning. We conduct a systematic empirical study of this approach using multi-facet data from 32 trained annotators across 4,200 preference judgments in a 4 × 4 × 4 factorial design. Our key findings: (1) The simulation approach achieves up to 9.9 percentage point improvements over the Base Judge; (2) Reasoning traces provide the largest gains with higher collection efforts, while interface telemetry often hurts rather than helps performance despite being cheaper to collect. (3) Simulation difficulty is systematic, predicted by an evaluator’s neutral usage (most clearly on Helpfulness) and divergence from consensus; the neutral-usage tendency—rather than simulatability itself—is the cross-task-stable property (r = 0.728). These results establish both the potential and limits of evaluator-specific auxiliary data for personalized evaluation, offering methodological insights for scaling individual aware AI assessment.

Rewriting inputs to improve frozen downstream models has become a common strategy in modern NLP pipelines. Prior work on incremental dialogue discourse parsing (DDP) shows that supervised clarification models can rewrite fragmentary or underspecified utterances—such as resolving ellipsis or references—to improve parsing accuracy. In this work, we revisit this idea under realistic deployment conditions, where no clarification supervision is available and the clarifier must rely on zero-shot prompting or feedback from a frozen parser. Across three Segmented Discourse Representation Theory (SDRT) datasets and multiple parsers, we find that last-utterance clarification is far less reliable than suggested by supervised settings. Parser-agnostic rewriting often introduces more regressions than repairs, as edits that enable fixes also disrupt discourse cues relied upon by the parser. A best-of-8 rewriting analysis further reveals a practical ceiling: a large fraction of errors are not repairable through input rewriting alone. A parser-aware clarifier trained with GRPO reduces regressions by up to 37% by learning conservative abstention, yet still fails to produce selectivity-aware clarifications that consistently improve parsing. Together, these findings recast clarification as a selective intervention problem. We identify rewritability prediction—deciding whether an utterance is repairable before intervention—as the key missing capability for input-side optimization of frozen discourse parsers, and a critical direction for improving agentic pipelines more broadly.[Data and code are available at https://github.com/ounlp/Clarification-for-DDP.]

While dense retrieval models have been the standard for state-of-the-art information retrieval, their deployment is often constrained by high memory requirements and reliance on GPU accelerators for vector similarity search at scale. Learned sparse retrieval offers a compelling alternative by enabling efficient search via inverted indices, yet it has historically received less attention than dense approaches. In this paper, we introduce LACONIC, a family of learned sparse retrievers based on the Llama3 architecture (1B, 3B, and 8B). We propose a streamlined two-phase training curriculum consisting of (1) weakly supervised pre-finetuning to adapt causal LLMs for bidirectional contextualization and (2) high-signal finetuning using curated hard negatives. Our results demonstrate that LACONIC effectively bridges the performance gap with dense models: the 8B variant achieves a state-of-the-art 60.2 nDCG@10 on the MTEB Retrieval benchmark, ranking 15th on the leaderboard as of February 5th, 2026, while utilizing 74% less index memory than an equivalent dense model. By delivering high retrieval effectiveness on commodity CPU hardware with a fraction of the compute budget required by competing models, LACONIC provides a scalable and efficient solution for real-world search applications. We fully open source our code implementation and trained checkpoints to facilitate reproducibility.

Transformer-based document cross-encoder rerankers are a central component of modern information retrieval systems. Despite their success, these models suffer from high computational costs due to processing long query-document sequences at inference time. A known approach to improve efficiency is token compression, which consists of aggregating groups of tokens together in the initial embedding layer, reducing the effective number of tokens and making the computation faster. While token compression has proven to be successful for bi-encoder retrievers, we empirically observed that this approach may be ineffective for cross-encoder rerankers. In this paper, we propose Layer-wise Token Compression (LTC), which applies adaptive token pooling at intermediate transformer layers. Through extensive ablation studies on MS MARCO passage and document ranking tasks, we demonstrate that compression at middle layers preserves ranking quality while increasing inference QPS by up to 25% for passage ranking and up to 116% for document ranking. We also extend LTC to listwise LLM rerankers and show that the same approach can be easily applied to long-context listwise reranking, where the QPS improvements are even greater. More surprisingly, when applying rerankers trained on short passages to long-document ranking tasks, models trained with compression outperform their uncompressed counterparts, suggesting that compression may act as a beneficial regularizer that encourages length-invariant representations.

Kiran Ramnath, Kang Zhou, Sheng Guan, Soumya Smruti Mishra, Xuan Qi, Zhengyuan Shen, Shuai Wang, Sangmin Woo, Sullam Jeoung, Yawei Wang, Haozhu Wang, Han Ding, Yuzhe Lu, Zhichao Xu, Yun Zhou, Balasubramaniam Srinivasan, Qiaojing Yan, Yueyan Chen, Haibo Ding, Panpan Xu, Lin Lee Cheong. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Recommender systems (RSs) are susceptible to Interaction-level Membership Inference Attacks (IMIAs), which aim to determine whether specific user-item interactions are present in the training data of the target RS. However, existing IMIAs struggle with inferring the membership of tail interactions, i.e., the interactions involving tail items, due to the limited information available about these items. This paper introduces MINER, a new IMIA designed to enhance attack performance against RSs with long-tailed item distribution. MINER addresses the information scarcity of tail items at both the feature and sample levels. At the feature level, MINER leverages the Knowledge Graphs (KGs) to obtain the auxiliary knowledge of tail items. At the sample level, MINER designs a Bilateral-Branch Network (BBN) as the attack model. The BBN trains two branches independently, with one branch trained on interaction samples with the original long-tailed item distribution and the other on interaction samples with a more balanced item distribution. The outputs of the two branches are aggregated using a cumulative learning component. Our experimental results demonstrate that MINER significantly enhances the attack accuracy of IMIA, especially for tail interactions. Beyond attack design, we design a defense mechanism named RGL to defend against MINER. Empirical evaluations demonstrate that RGL effectively mitigates the privacy risks posed by MINER while preserving recommendation accuracy. Our code is available at https://github.com/dzhong2/MINER.

Conversational search has seen increased recent attention in both the IR and NLP communities. It seeks to clarify and solve users' search needs through multi-turn natural language interactions. However, most existing systems are trained and demonstrated with recorded or artificial conversation logs. Eventually, conversational search systems should be trained, evaluated, and deployed in an open-ended setting with unseen conversation trajectories. A key challenge is that training and evaluating such systems both require a human-in-the-loop, which is expensive and does not scale. One strategy is to simulate users, thereby reducing the scaling costs. However, current user simulators are either limited to only responding to yes-no questions from the conversational search system or unable to produce high-quality responses in general.

State-of-the-art industrial-level recommender system applications mostly adopt complicated model structures such as deep neural networks. While this helps with the model performance, the lack of system explainability caused by these nearly blackbox models also raises concerns and potentially weakens the users’ trust in the system. Existing work on explainable recommendation mostly focuses on designing interpretable model structures to generate model-intrinsic explanations. However, most of them have complex structures, and it is difficult to directly apply these designs onto existing recommendation applications due to the effectiveness and efficiency concerns. However, while there have been some studies on explaining recommendation models without knowing their internal structures (i.e., model-agnostic explanations), these methods have been criticized for not reflecting the actual reasoning process of the recommendation model or, in other words,faithfulness. How to develop model-agnostic explanation methods and evaluate them in terms of faithfulness is mostly unknown. In this work, we propose a reusable evaluation pipeline for model-agnostic explainable recommendation. Our pipeline evaluates the quality of model-agnostic explanation from the perspectives of faithfulness and scrutability. We further propose a model-agnostic explanation framework for recommendation and verify it with the proposed evaluation pipeline. Extensive experiments on public datasets demonstrate that our model-agnostic framework is able to generate explanations that are faithful to the recommendation model. We additionally provide quantitative and qualitative study to show that our explanation framework could enhance the scrutability of blackbox recommendation model. With proper modification, our evaluation pipeline and model-agnostic explanation framework could be easily migrated to existing applications. Through this work, we hope to encourage the community to focus more on faithfulness evaluation of explainable recommender systems.

Ranking systems are the key components of modern Information Retrieval (IR) applications, such as search engines and recommender systems. Besides the ranking relevance to users, the exposure fairness to item providers has also been considered an important factor in ranking optimization. Many fair ranking algorithms have been proposed to jointly optimize both ranking relevance and fairness. However, we find that most existing fair ranking methods adopt greedy algorithms that only optimize rankings for the next immediate session or request. As shown in this paper, such a myopic paradigm could limit the upper bound of ranking optimization and lead to suboptimal performance in the long term.

Smart contract and DApp users are taking great risks, as they do not obtain necessary knowledge that can help them avoid using vulnera- ble and malicious contract code. In this paper, we develop a novel system Tx2TXT that can automatically create security-centric textual descriptions directly from smart contract bytecode. To capture the security aspect of financial applications, we formally define a funds transfer graph to model critical funds flows in smart contracts. To ensure the expressiveness and conciseness of the descriptions de- rived from these graphs, we employ a GCN-based model to identify security-related condition statements and selectively add them to our graph models. To convert low-level bytecode instructions to human- readable textual scripts, we leverage robust API signatures to recover bytecode semantics. We have evaluated Tx2TXT on 890 well-labeled vulnerable, malicious and safe contracts where developer-crafted descriptions are available. Our results have shown that Tx2TXT out- performs state-of-the-art solutions and can effectively help end users avoid risky contracts

Query-focused summarization (QFS) aims to provide a summary of a document that satisfies information need of a given query and is useful in various IR applications, such as abstractive snippet generation. Current QFS approaches typically involve injecting additional information, e.g. query-answer relevance or fine-grained token-level interaction between a query and document, into a finetuned large language model. However, these approaches often require extra parameters & training, and generalize poorly to new dataset distributions. To mitigate this, we propose leveraging a recently developed constrained generation model Neurological Decoding (NLD) as an alternative to current QFS regimes which rely on additional sub-architectures and training. We first construct lexical constraints by identifying important tokens from the document using a lightweight gradient attribution model, then subsequently force the generated summary to satisfy these constraints by directly manipulating the final vocabulary likelihood. This lightweight approach requires no additional parameters or finetuning as it utilizes both an off-the-shelf neural retrieval model to construct the constraints and a standard generative language model to produce the QFS. We demonstrate the efficacy of this approach on two public QFS collections achieving near parity with the state-of-the-art model with substantially reduced complexity.

Ranking systems are ubiquitous in modern Internet services, including online marketplaces, social media, and search engines. Traditionally, ranking systems only focus on how to get better relevance estimation. When relevance estimation is available, they usually adopt a user-centric optimization strategy where ranked lists are generated by sorting items according to their estimated relevance. However, such user-centric optimization ignores the fact that item providers also draw utility from ranking systems. It has been shown in existing research that such user-centric optimization will cause much unfairness to item providers, followed by unfair opportunities and unfair economic gains for item providers.

Different from shopping at retail stores, consumers on e-commerce platforms usually cannot touch or try products before purchasing, which means that they have to make decisions when they are uncertain about the outcome (e.g., satisfaction level) of purchasing a product. To study people's preferences with regard to choices that have uncertain outcomes, economics researchers have proposed the hypothesis of Expected Utility (EU) that models the subject value associated with an individual's choice as the statistical expectations of that individual's valuations of the outcomes of this choice. Despite its success in studies of game theory and decision theory, the effectiveness of EU, however, is mostly unknown in e-commerce recommendation systems. Previous research on e-commerce recommendation interprets the utility of purchase decisions either as a function of the consumed quantity of the product or as the gain of sellers/buyers in the monetary sense. As most consumers just purchase one unit of a product at a time and most alternatives have similar prices, such modeling of purchase utility is likely to be inaccurate in practice. In this paper, we interpret purchase utility as the satisfaction level a consumer gets from a product and propose a recommendation framework using EU to model consumers' behavioral patterns. We assume that consumer estimates the expected utilities of all the alternatives and choose products with maximum expected utility for each purchase. To deal with the potential psychological biases of each consumer, we introduce the usage of Probability Weight Function (PWF) and design our algorithm based on Weighted Expected Utility (WEU). Empirical study on real-world e-commerce datasets shows that our proposed ranking-based recommendation framework achieves statistically significant improvement against both classical Collaborative Filtering/Latent Factor Models and state-of-the-art deep models in top-K recommendation.