论文检索

Guanghao Jin, Jingpei Wu, Tianpei Guo, Yiyi Niu, Weidong Zhou, Linyi Yang, Guoyang Liu

While Multimodal Large Language Models (MLLMs) have demonstrated the capacity for multi-modal reasoning, current Referring Expression Comprehension (REC) benchmarks lag behind, predominantly relying on intra-image cues and neglecting the integration of external world knowledge, which significantly impedes the evolution of REC towards real-world applications. This limitation obscures a model’s true capability to conduct textual reasoning (entity resolution), resolve spatial location (visual grounding), and verify reference validity (hallucination rejection). To address this, we introduce KnowDR-REC, a targeted audit benchmark comprising 1,042 positive triplets derived from real-world knowledge, along with rigorously matched negative samples. Unlike traditional datasets, we implement a controllable counterfactual evaluation mechanism that subjects textual expressions to single-factor perturbations (entity, relation, or time) to test sensitivity to fine-grained factual changes. Extensive evaluation of 18 state-of-the-art LMMs exposes a critical “binding hallucination,” revealing that current high performance is often built on fragile visual shortcuts rather than true understanding. KnowDR-REC thus serves as a pivotal diagnostic instrument, steering future research toward the genuine integration of perception and reasoning.

Zehua Wang, Zhaojin Zhang, Boyu Qiu, Xiaolong Weng, Ying Xiong, Buzhou Tang, Min Zhang

Retrieval-Augmented Generation (RAG) has been widely adopted to enhance large language models (LLMs) by incorporating external knowledge. However, the two main existing paradigms struggle with multi-hop reasoning: aggregate-first approaches suffer from high construction costs and limited adaptability to dynamic knowledge, while dynamic-first approaches rely heavily on LLM reasoning and are prone to error propagation across reasoning steps. To address these limitations, we propose SR-RAG, a symbolic reasoning framework for multi-hop question answering. SR-RAG integrates the advantages of both paradigms by dynamically generating sub-questions, performing information retrieval and symbolic encoding based on an on-the-fly graph, and using a symbolic verifier to formally validate intermediate reasoning steps to ensure the correctness of intermediate answers and the completeness of the reasoning chain . We evaluate SR-RAG on multiple multi-hop benchmarks and a medical dataset. Experimental results demonstrate that it significantly improves both accuracy and robustness.

Hyunjong Ok, Jaeho Lee

Large language models exhibit surprising sensitivity to the structure of the prompt, but the mechanisms underlying this sensitivity remain poorly understood. In this work, we conduct an in-depth investigation on a striking case: in multiple-choice question answering, placing context before the questions and options (CQO) outperforms the reverse order (QOC) by over 14%p, consistently over a wide range of models and datasets. Through systematic architectural analysis, we identify causal attention as the core mechanism: in QOC prompts, the causal mask prevents option tokens from attending to context, creating an information bottleneck where context becomes invisible to options.

Tong Zhang, Yang Wu, Yufei Shi, Rujing Yao, Zhuoren Jiang, Xiaozhong Liu

In heterogeneous scientific teams, proactive team agents can serve as effective assistants regarding the research progress of the project. However, proactive agents always suffer from collaborative myopia: a greedy optimization for immediate task accuracy which ignore the long-term goal of team sustainability. This leads to the Individual-centric Trap, where capable experts (e.g., PIs) are disproportionately overloaded while Junior roles remain underutilized. Therefore, neglecting opportunity costs in task allocation can implicitly erodes the enduring performance of the team. To solve this imbalance between efficiency and sustainability, we propose GT-PMARL (Game-Theoretic Proactive Multi-Agent Reinforcement Learning). By internalizing the opportunity cost as a key consideration in individual decision-making, the collaboration logic of agents has been reshaped. Our framework employs: (1) a Positive-Unlabeled scorer to anchor intervention quality under sparse supervision; (2) a Nash-Pareto competitive objective to seek an equilibrium between individual task excellence and collective load balancing. Empirical experiments in scientific workflows show that GT-PMARL effectively maintains high performance while preventing experts from over-developing. Our work provides a scalable paradigm for building a sustainable and balanced human-AI collaborative ecosystem.

Zhengliang Shi, Ruotian Ma, Jen-tse Huang, Xinbei Ma, Xingyu Chen, Mengru Wang, Qu Yang, Yue Wang, Fanghua Ye, Ziyang Chen 等

Large language models (LLMs) are increasingly entrusted with high-stakes decisions that affect human welfare. However, the principles and values that guide these models when distributing scarce societal resources remain largely unexamined. To address this, we introduce the Social Welfare Function (SWF) Benchmark, a dynamic simulation environment in which an LLM acts as a dictator, distributing tasks to heterogeneous recipients with different returns on investment (ROI). The benchmark is designed to create a dilemma between maximizing collective efficiency (i.e., overall ROI) and ensuring distributive fairness (measured by the Gini coefficient). We evaluate 20 state-of-the-art LLMs. Our findings reveal several key insights, including: (i) LLMs’ general ability, as measured by popular Arena leaderboards, misaligns with their allocation skills; (ii) Most LLMs exhibit a strong default utilitarian orientation, prioritizing overall productivity at the expense of inequality. (iii) Allocation behaviors are highly manipulated, easily perturbed by common persuasion strategies. These results highlight the risks of deploying current LLMs as societal decision-makers and underscore the need for specialized benchmarks and alignment for AI governance.

Srujan P Mule, Aniketh Garikaparthi, Manasi Patwardhan

As language models accelerate scientific research by automating hypothesis generation and implementation, a new bottleneck emerges: evaluating and filtering hundreds of AI-generated ideas without exhaustive experimentation. We ask whether LMs can learn to forecast the empirical success of research ideas before any experiments are run. We study comparative empirical forecasting: given a benchmark-specific research goal and two candidate ideas, predict which will achieve better benchmark performance. We construct a dataset of 11,488 idea pairs grounded in objective outcomes from PapersWithCode. While off-the-shelf 8B-parameter models struggle (30% acc.), SFT dramatically boosts performance to 77.1%, outperforming GPT-5 (61.1%). By framing evaluation as a reasoning task via Reinforcement Learning with Verifiable Rewards (RLVR), we train models to discover latent reasoning paths, achieving 71.35% acc. with interpretable justifications. Through additional ablations and out-of-distribution tests, we show robustness to surface-level heuristics and transfer to both a cross-domain time-split test set and an independently constructed test set. Our results demonstrate that compute-efficient small language models can serve as effective, objective verifiers, offering a scalable path for autonomous scientific discovery.

Bhavik Chandna, Procheta Sen

Explainability has become a crucial concern in today’s world, aiming to enhance transparency in machine learning and deep learning models. Information retrieval is no exception to this trend. In existing literature on explainability of information retrieval, the emphasis has predominantly been on illustrating the concept of relevance concerning a retrieval model. The questions addressed include why a document is relevant to a query, why one document exhibits higher relevance than another, or why a specific set of documents is deemed relevant for a query. However, limited attention has been given to understanding why a particular document is not favored (e.g., not within top-K) with respect to a query and a retrieval model. In an effort to address this gap, our work focuses on the question of what terms need to be added within a document to improve its ranking. This, in turn, answers the question of which words in the document played a role in not being favored by a retrieval model for a particular query. We use a counterfactual framework to solve the above-mentioned research problem. Our experiments show the effectiveness of our proposed approach in predicting counterfactuals for both statistical (e.g. BM25) and deep-learning-based models (e.g. DRMM, DSSM, ColBERT, MonoT5).

Jiantong Jiang, Peiyu Yang, Rui Zhang, Feng Liu

Despite the rapid advancements of large language models (LLMs), LLM serving systems remain memory-intensive and costly. The key-value (KV) cache, which stores KV tensors during autoregressive decoding, is crucial for enabling low-latency, high-throughput LLM inference serving. In this survey, we focus on system-aware KV infrastructure for serving LLMs (abbreviated as sKis). We revisit recent work from a system behavior perspective, organizing existing efforts into three dimensions: execution and scheduling (temporal), placement and migration (spatial), and representation and retention (structural). Furthermore, we analyze cross-behavior co-design affinity and behavior-objective links, highlighting future opportunities. Our work systematizes a rapidly evolving area, providing a foundation for understanding and innovating KV cache designs in modern LLM serving infrastructure.

Fanding Huang, Guanbo Huang, Xiao Fan, Yi He, Xiao Liang, Xiao Chen, Qinting Jiang, Faisal Nadeem Khan, Jingyan Jiang, Zhi Wang

Reinforcement Learning with Verifiable Rewards (RLVR) for LLM reasoning is often framed as balancing exploration and exploitation in action space, typically operationalized with token-level proxies (e.g., output entropy or confidence). We argue that this apparent trade-off is largely a measurement artifact: token-level statistics reflect next-token uncertainty rather than how reasoning progresses over multi-token semantic structures. We therefore study exploration and exploitation in the hidden-state space of response trajectories. We use Effective Rank (ER) to quantify representational exploration and introduce its temporal derivatives, Effective Rank Velocity (ERV) and Effective Rank Acceleration (ERA), to characterize exploitative refinement dynamics. Empirically and theoretically, ER and ERV exhibit near-zero correlation in semantic space, suggesting the two capacities can be improved simultaneously. Motivated by this, we propose Velocity-Exploiting Rank Learning (VERL), which shapes the RL advantage with an auxiliary signal derived from ER/ERV and uses the more stable ERA as a meta-control variable to adaptively balance the incentives. Across multiple base models, RL algorithms, and reasoning benchmarks, VERL yields consistent improvements, including large gains on challenging tasks (e.g., 21.4% in Gaokao 2024).

Qihua Dong, Ruozhen He, Junwen Chen, Yizhou Wang, Xu Ma, Songyao Jiang, Yun Fu

Advanced chart question answering requires both precise perception of small visual elements and multi-step reasoning across several subplots. While existing MLLMs are strong at understanding single plots, they often struggle with multi-step reasoning across multiple subplots. We propose HierVA, a hierarchical visual agent framework for chart reasoning that iteratively constructs and updates a working context in a joint image–text space. A high-level manager generates plans and maintains a compact context containing only key information, while specialized sub-agents perform reasoning, gather evidence, and return results. In particular, the agent maintains separate visual and textual contexts, using a zoom-in tool to restrict the visual context. Experiments on the chart reasoning benchmarks demonstrate consistent improvements over strong multimodal baselines, and ablation studies verify that hierarchical architecture, limited visual context, and distilled context contribute complementary gains.

Wenhao Li, Yuwei Yang, Xiaoqing Wu, Yufeng Han, Cunliang Kong, Yuzhuo Bai, Xin Cong, Maosong Sun

While Large Language Models (LLMs) demonstrate remarkable capabilities in open-ended creative generation, they notably struggle with Format-Constrained Generation tasks—such as poetry and lyrics—where strict adherence to multidimensional structural constraints (i.e., format, phonetics, and rhyme) is prerequisite to aesthetic value. Existing paradigms predominantly rely on unreliable prompting or rigid constrained decoding strategies; the former often fails to ensure compliance, while the latter compromises inference latency and disrupts the natural probability distribution, degrading generation quality. To bridge this gap, we establish CCP-Arena, a rigorous testbed for Chinese Classical Poetry, and proposeProgressive Structural Internalization (PSI) a novel framework designed to embed external constraints into the model’s intrinsic intuition. PSI initiates withStructural Scaffolding via Explicit Cognitive Planning, utilizing explicit template to provide a structural scaffold for subsequent generation. This is followed by a Cascaded Reinforcement Learning stage guided by a Holistic Reward Model, which optimizes for precise structural-semantic alignment. Extensive experiments demonstrate that PSI achieves state-of-the-art performance, surpassing baselines in both strict constraint adherence and literary aesthetics. Furthermore, mechanistic analysis confirms that our method effectively internalizes structural information into the model’s latent representations, offering a robust and efficient solution for constrained creative generation.

Cennet Oguz, Yasser Hamidullah, Josef van Genabith, Simon Ostermann

Evaluating factual correctness in procedural video captions is challenging because captions must reflect both the abstract procedural roles (e.g., actions, ingredients, tools, locations) and their visual execution. Existing evaluation metrics, which rely on lexical overlap or holistic semantic similarity, often miss role-specific omissions and misclassify visually present but task-irrelevant content as hallucinations. We introduce DualFact+, a role-aware, fact-level evaluation framework that distinguishes conceptual facts, encoding ontology-based role typing of procedural steps (Action, Object or Ingredient, Tool, Location), from contextual facts, encoding video-grounded predicate–argument relations that specify how these roles are instantiated during execution. To enable complete and role-consistent evaluation, DualFact+ incorporates visually grounded implicit arguments and contrastive fact sets, and operates in two complementary modes: DualFact-C for text-based verification and DualFact-V for video-grounded verification. Experiments on YouCook3-Fact and CraftBench-Fact show that state-of-the-art captioning models produce fluent but often incomplete descriptions with systematic role-level errors. DualFact+ achieves stronger correlation with human factuality judgments than standard lexical and embedding-based metrics, highlighting the importance of role-aware evaluation for procedural video understanding.

Yulia Otmakhova, Matteo Guida, Lea Frermann

Metaphors are powerful framing devices, yet their source domains alone do not fully explain the specific associations they evoke. We argue that the interplay between source domains and semantic frames determines how metaphors shape understanding of complex issues, and present a computational framework that allows to derive salient discourse metaphors through their source domains and semantic frames. Applying this framework to climate change news, we uncover not only well-known source domains but also reveal nuanced frame-level associations that distinguish how the issue is portrayed. In analyzing immigration discourse across political ideologies, we demonstrate that liberals and conservatives systematically employ different semantic frames within the same source domains, with conservatives favoring frames emphasizing uncontrollability and liberals choosing neutral or more “victimizing” semantic frames. Our work bridges conceptual metaphor theory and linguistics, providing the first NLP approach for discovery of discourse metaphors and fine-grained analysis of differences in metaphorical framing.

Zhenghai Chen, Senbin Xu, Jiaxi Tan, Xinhua Wu, Yan Zhang, Xiawu Zheng, Shengchuan Zhang, Ke Li, Sicheng Zhao, Liujuan Cao 等

Factual knowledge stored in Large Language Models (LLMs) inevitably becomes outdated or erroneous over time, making it critical to update these models without incurring the high cost of retraining. Existing sequential knowledge editing methods predominantly rely on strict orthogonal projection to preserve previously edited knowledge. However, this excessive constraint limits gradient expressiveness, resulting in a significant degradation of model generalization and overall performance as the number of edits increases. To address this challenge, we propose Dual-Importance Projection Editing (DipEdit). This method leverages Singular Value Decomposition (SVD) to identify critical gradient subspaces and introduces a dual mechanism comprising "accumulated importance" and "projection importance." Unlike traditional approaches that enforce strict orthogonality, DipEdit dynamically scales gradient components parallel to key subspaces based on their projection importance rather than discarding them directly. This approach enhances the model’s adaptability to new knowledge while maximally preserving historical knowledge. Extensive experiments conducted on five mainstream LLMs using the ZsRE and Counterfact datasets demonstrate that DipEdit effectively handles thousands of sequential edits. The proposed method achieves an average comprehensive performance improvement of 10.36% and effectively maintains the model’s general capabilities on downstream tasks. Code is available at: https://github.com/czhhhla/DipEdit.

Benedikt Ebing, Lennart Keller, Goran Glavaš

Exposing latent lexical overlap, script romanization has emerged as an effective strategy for improving cross-lingual transfer (XLT) in multilingual language models (mLMs). Most prior work, however, focused on setups that favor romanization the most: **(1)** transfer from high-resource Latin-script to low-resource non-Latin-script languages and/or **(2)** between genealogically closely related languages with different scripts. It thus remains unclear whether romanization is a good representation choice for *pretraining* general-purpose mLMs, or, more precisely, if information loss associated with romanization harms performance for high-resource languages. We address this gap by pretraining encoder LMs from scratch on both romanized and original texts for six typologically diverse high-resource languages, investigating two potential sources of degradation: **(i)** loss of script-specific information and **(ii)** dilution of language-specific representations from increased subword overlap. Using two romanizers with different fidelity profiles, we observe negligible performance loss for languages with segmental scripts, whereas languages with morphosyllabic scripts (Chinese and Japanese) suffer degradation that higher-fidelity romanization mitigates but cannot fully recover. Importantly, comparing monolingual LMs with their mLM counterpart, we find no evidence that increased subword overlap dilutes language-specific representations. We further show that romanization improves encoding efficiency (i.e., fertility) for segmental scripts at a negligible performance cost.

Sandeep Kumar, Yash Kamdar, Abid Hossain, Bharti Kumari, Tanik Saikh, Asif Ekbal

Scientific peer reviews frequently contain conflicting expert judgments, and the increasing scale of conference submissions makes it challenging for Area Chairs and editors to reliably identify and interpret such disagreements. Existing approaches typically frame reviewer disagreement as binary contradiction detection over isolated sentence pairs, abstracting away the review-level context and obscuring differences in the severity of evaluative conflict. In this work, we introduce a fine-grained formulation of reviewer contradiction analysis that operates over full peer reviews by explicitly identifying contradiction evidence spans and assigning graded disagreement intensity scores. To support this task, we present RevCI, an expert-annotated benchmark of peer-review pairs with evidence-level contradiction annotations with graded intensity labels. We further propose IMPACT, a structured multi-agent framework that integrates aspect-conditioned evidence extraction, deliberative reasoning, and adjudication to model reviewer contradictions and their intensity. To support efficient deployment, we distill IMPACT into TIDE, a small language model that predicts contradiction evidence and intensity in a single forward pass. Experimental results show that IMPACT substantially outperforms strong single-agent and generic multi-agent baselines in both evidence identification and intensity agreement, while TIDE achieves competitive performance at significantly lower inference cost.

Yehonatan Peisakhovsky, Zorik Gekhman, Yosi Mass, Liat Ein-Dor, Roi Reichart

Context-grounded hallucinations are cases where model outputs contain information not verifiable against the source text. We study the applicability of LLMs for localizing such hallucinations, as a more practical alternative to existing complex evaluation pipelines. In the absence of established benchmarks for meta-evaluation of hallucinations localization, we construct one tailored to LLMs, involving a challenging human annotation of over 1,000 examples. We complement the benchmark with an LLM-based evaluation protocol, verifying its quality in a human evaluation. Since existing representations of hallucinations limit the types of errors that can be expressed, we propose a new representation based on free-form textual descriptions, capturing the full range of possible errors. We conduct a comprehensive study, evaluating four large-scale LLMs, which highlights the benchmark’s difficulty, as the best model achieves an F1 score of only 0.67. Through careful analysis, we offer insights into optimal prompting strategies for the task and identify the main factors that make it challenging for LLMs: (1) a tendency to incorrectly flag missing details as inconsistent, despite being instructed to check only facts in the output; and (2) difficulty with outputs containing factually correct information absent from the source - and thus not verifiable - due to alignment with the model’s parametric knowledge.

Seohyeong Lee, Eunwon Kim, Hwaran Lee, Buru Chang

Human preference data is essential for aligning large language models (LLMs) with human values, but collecting such data is often costly and inefficient-motivating the need for efficient data selection methods that reduce annotation costs while preserving alignment effectiveness. To address this issue, we propose Alignment Data Map, a data analysis tool for identifying and selecting effective preference data. We first evaluate alignment scores of the preference data by LLM-as-a-judge, explicit reward model, and reference-based approaches. The Alignment Data Map considers both response quality and inter-response variability based on the alignment scores. From our experimental findings, training on only 33% of samples that exhibit high-quality and low-variability, achieves comparable or superior alignment performance on MT-Bench, Evol-Instruct, and AlpacaEval, compared to training with the full dataset. In addition, Alignment Data Map detects potential label misannotations by analyzing correlations between annotated labels and alignment scores, improving annotation accuracy. The implementation is available at https://github.com/01choco/Alignment-Data-Map.

Bang Zhang, Ruotian Ma, Qingxuan Jiang, Peisong Wang, Jiaqi Chen, Zheng Xie, Xingyu Chen, Yue Wang, Fanghua Ye, Jian Li 等

Assessing how well a large language model (LLM) understands human, rather than merely text, remains an open challenge.To bridge the gap, we introduce Sentient Agent as a Judge(SAGE), an automated evaluation framework that measures an LLM’s higher-order social cognition.SAGE instantiates a “Sentient Agent” – an LLM-powered agent that simulates human-like emotional changes and inner thoughts to provide a more realistic evaluation of the tested model in multi-turn conversations.At every turn, the agent reasons about (i) how its emotion changes, (ii) how it feels, and (iii) how it should reply, yielding a numerical emotion trajectory and interpretable inner thoughts.Experiments on 100 supportive-dialogue scenarios show that the final Sentient emotion score correlates strongly with Barrett-Lennard Relationship Inventory (BLRI) ratings and utterance-level empathy metrics, validating psychological fidelity. Human evaluation further demonstrates 85.3% consistency between the agent’s emotional reasoning and human judgments. We also build a public Sentient Leaderboard covering 18 commercial and open-source models that uncovers substantial gaps (up to 4\times) between frontier systems (GPT-4o-Latest, Gemini2.5-Pro) and earlier baselines, gaps not reflected in conventional leaderboards (e.g. Arena). SAGE thus provides a principled, scalable, and interpretable tool for tracking progress toward genuinely empathetic and socially adept language agents.

Tianyi Xu, Zhe Zhao, Tianshuo Wei, Yiqun Kou, Liuliu Han, Ye Wei

The escalating demand for comprehensive literature surveys in rapidly evolving research areas makes manual writing increasingly impractical, underscoring the necessity of automation. Large Language Models (LLMs) provide a promising foundation for this task, yet guiding them to generate accurate, reliable content remains a fundamental challenge, as issues such as hallucinations and vague organization often persist. To address this, we propose FIKSurvey, a feedback-driven framework grounded in the idea that “Feedback is the key for automatic survey generation.” Specifically, FIKSurvey systematically incorporates feedback across three dimensions: outline feedback for structural clarity, citation feedback for evidence validation, and content feedback for readability and analytical depth. The framework also supports optional human-in-the-loop intervention for user-specific needs. Experiments confirm that FIKSurvey substantially improves both citation and content quality, demonstrating feedback as the critical mechanism for automatic survey generation.