论文检索

Qian Ma, Qiong Wu, Zhengyi Zhou, Yao Ma

Knowledge-Based Visual Question Answering (KB-VQA) requires grounding visual queries to external knowledge beyond directly observable content in images.While recent multi modal large language models (MLLMs) show strong perceptual abilities, they struggle on KB-VQA tasks requiring groundings from both fine-grained entity and evidence levels.Most existing multi-modal retrieval augmented generation (MM-RAG) methods tightly couple entity discrimination and section-level evidence ranking into a single re-ranking stage, leading to high cost and limited generalization.In this work, we revisit existing MM-RAG solutions from a workflow perspective and argue both entity-level and fact-level groundings are key bottlenecks.We observe that although MLLMs often fail under open-ended entity naming, they can better identify the correct entity when selecting from a small set of candidate names.Based on this insight, we propose a simple and training-free identify-before-answer IBA framework that decouples entity identification from section-level re-ranking.Our approach prompts an MLLM to select high-confidence entities using only candidate names, followed by an off-the-shelf textual re-ranker for evidence selection.Experiments on Encyclopedic-VQA and InfoSeek show that our method consistently outperforms fine-tuned multi-modal re-ranking baselines while reducing training and inference complexity.Additional analyses reveal that the improvements arise not only from better entity identification, but also from selecting more informative evidence once correct entity is fixed.Our implementation is made public to ease reproducibility

Yiyuan Yang, Zichuan Liu, Lei Song, Kai Ying, Stephen Wang, Joshua Thomas Bamford, Svitlana Vyetrenko, Jiang Bian, Qingsong Wen

Time series anomaly detection (TSAD) has traditionally focused on binary classification and often lacks the fine-grained categorization and explanatory reasoning required for transparent decision-making. To address these limitations, we propose Time-series Reasoning for Anomaly (Time-RA), a novel task that reformulates TSAD from a discriminative into a generative, reasoning-intensive paradigm. To facilitate this, we introduce RATs40K, the first real-world large-scale multimodal benchmark with ~40,000 samples across 10 domains, integrating raw time series, textual context, and visual plots with structured reasoning annotations. Extensive benchmarking shows that while supervised fine-tuning and visual representations boost diagnostic accuracy and reasoning consistency, performance varies across complex scenarios. Notably, fine-tuned models demonstrate strong "plug-and-play" transferability, outperforming traditional baselines on unseen real-world datasets. Our work establishes a foundation for interpretable, multimodal time series analysis. All code and the RATs40K dataset are fully open-sourced to facilitate future research.

Mike Zhang, Johannes Bjerva, Russa Biswas

We introduce fs1, a simple yet effective method that improves the factuality of reasoning traces by sourcing them from large reasoning models and grounding them by conditioning on knowledge graph (KG) paths. We fine-tune eight instruction-tuned Large Language Models (LLMs) on 3.9K factually grounded reasoning traces and rigorously evaluate them on six complex open-domain question-answering (QA) benchmarks encompassing 23.9K questions. Our results demonstrate that our fs1-tuned model consistently outperforms instruction-tuned counterparts with parallel sampling by 6-14 absolute points (pass@). Our detailed analysis shows that fs1 considerably improves model performance over more complex questions (requiring 3 or more hops on KG paths) and numerical answer types compared to the baselines. Furthermore, in single-pass inference, we notice that smaller LLMs show the most improvements. While prior works demonstrate the effectiveness of reasoning traces primarily in the STEM domains, our work shows strong evidence that anchoring reasoning to factual KG paths is a critical step in transforming LLMs for reliable knowledge-intensive tasks.

Md. Mahadi Hassan, John Salvador, Akond Rahman, Santu Karmaker

LLMs show promise in code generation, yet their effectiveness for IT automation tasks, particularly for tools like Ansible, remains understudied. Existing benchmarks rely primarily on synthetic tasks that fail to capture the needs of practitioners who use IT automation tools. We present ExITBench (Execution-based IT Automation Benchmark), a benchmark of 126 diverse tasks (e.g., configuring servers and managing files) in which each task captures state reconciliation - a core property of IT automation tools. ExITBench evaluates LLMs’ ability to generate functional Ansible automation scripts via dynamic execution in controlled environments. We evaluate 14 open-source and 3 proprietary LLMs and find that GPT-4.1-Mini achieves the best pass@10 rate of 23.9%, while Claude-3.5-Sonnet achieves the best pass@1 performance. To explain the low performance, we analyze 1,517 execution failures across the evaluated LLMs and identify two prevalent semantic error categories: failures in state-reconciliation reasoning (42.117% combined from variable (12.287%), host (10.363%), path (10.511%), and template (8.956%) issues) and deficiencies in module-specific execution knowledge (26.203% combined from attribute & parameter (17.617%) and module (8.586%) errors). Our findings reveal key limitations in LLMs’ ability to address state reconciliation and apply specialized module knowledge, indicating that reliable IT automation with LLM-based agents need major advances in state reasoning and domain-specific execution.

Chengyuan Jin, Ao Chang, Daojian Zeng, Wenhao Teng, Xiangwen Liao, Kang Liu, Jun Zhao, Yubo Chen

Temporal knowledge graph forecasting(TKGF) asks a model to rank the mostplausible future entity for a query such as(s, r, ?, t) from historical events. Recenttraining-free methods use large languagemodels (LLMs) for this task, but their accuracydepends heavily on which past events areshown in the prompt under a tight contextbudget. We present LANTERN, a training-freeprompting framework that addresses thisbottleneck by combining two complementaryviews of history: a long-window strengthscore for stable interaction patterns anda short-window novelty score for suddenchanges. LANTERN first filters unhelpfulevents, then selects a compact evidence setwith Pareto-greedy selection, and finally addsone structure-aware analogical demonstration.Across ICEWS14, ICEWS05-15, ICEWS18,and GDELT, LANTERN consistently outperforms the state-of-the-art training-free baselineAnRe under the same backbone and 2-hopcandidate protocol, improving Hits@1 by upto 2.5 points and MRR by up to 1.2 points.

Hossein Entezari Zarch, Lei Gao, Chaoyi Jiang, Murali Annavaram

Large reasoning models (LRMs) achieve state-of-the-art performance on challenging benchmarks by generating long chains of intermediate steps, but their inference cost is dominated by decoding, where each new token must attend to the entire growing sequence. One approach to reduce this latency is to evict entries from the key-value (KV) cache, thereby reducing the active context used in attention computation. However, such sparse attention methods suffer from severe accuracy degradation on reasoning tasks due to cumulative selection errors and the evolving importance of tokens over long derivations. We present DELTA, a training-free sparse attention mechanism that improves computational efficiency without sacrificing model accuracy. DELTA partitions transformer layers into three groups: initial layers that use full attention, a small set of Δ-layers that identify salient tokens via aggregated head-level attention scores, and subsequent sparse-attention layers that attend only to the selected subset. This design preserves the full KV cache in GPU memory for accuracy, while avoiding expensive full-attention computation over many layers. On reasoning benchmarks such as AIME and GPQA-Diamond, DELTA matches or surpasses full attention in accuracy, while reducing the number of attended tokens by up to 4.25× and delivering 1.54× end-to-end speedup. Our results show that selective reuse of intermediate attention maps offers a robust path toward efficient long-context reasoning. The code is available at https://github.com/hoenza/DELTA.

Ofir Shabat, Ido Guy, Kira Radinsky

Large Language Models (LLMs) are increasingly used to explain, summarize, and translate real-world events, including ongoing geopolitical conflicts. Yet it remains unclear whether they reproduce conflict-specific propaganda and, if so, how this appears in their outputs. We study this question for the Russia-Ukraine war through perspectival divergence, the extent to which model outputs align with competing narratives from different information ecosystems. We construct a conflict-aware evaluation set of neutral English event statements paired with Russian (RU)- and Ukrainian (UA)-oriented reference texts drawn from news outlets and Telegram channels. We then evaluate multiple LLMs under several prompting contexts using a reference-based semantic distance metric that measures directional proximity to RU- and UA-oriented references. To explain not only which side a model is closer to but also how that alignment is expressed, we further analyze outputs using five propaganda-relevant categories: Framing Narrative, Emotional Manipulation, Source Credibility, Social Pressure Identity, and Toponymy Naming. Across models, we find stable, model-specific leanings and technique profiles that persist across prompts and are not captured by standard factuality-oriented metrics. Our findings show that models that appear neutral under conventional evaluations can still encode systematic, conflict-specific propaganda patterns, underscoring the need for conflict-aware evaluation frameworks.

Kaiqu Liang, Haimin Hu, Ryan Liu, Thomas L. Griffiths, Jaime Fernández Fisac

While Reinforcement Learning from Human Feedback (RLHF) has shown promise in aligning generative AI, we present empirical evidence that it can also cause severe, systematic misalignment. We hypothesize that this stems from evaluator feedback depending on downstream outcome predictions (foresight) that can be influenced by the AI’s output, inducing Goodhart’s law dynamics. We present a theoretical analysis showing that conditioning evaluator feedback on downstream observations (hindsight) inhibits this effect by decoupling the alignment signal from potentially compromised predictions—crucially, the result holds even if the observed outcomes are sampled from the AI’s own world model. Building on this insight, we introduce Reinforcement Learning from Hindsight Simulation (RLHS), which presents plausible simulated outcomes to evaluators before eliciting feedback. We validate RLHS across three consultancy settings—marketplace interactions, restaurant recommendations, and online course advising—using both online (PPO) and offline (DPO) fine-tuning methods, and show that it substantially improves alignment over RLHF in experiments and human evaluations. We perform post-hoc benchmark evaluations on TruthfulQA, HaluEval, and TrustLLM, finding that even after single-task fine-tuning, RLHF misalignment persists, while RLHS consistently outperforms baselines and demonstrates strong out-of-domain generalization.

Liqiang Jing, Viet Dac Lai, Seunghyun Yoon, Trung Bui, Xinya Du

Video Multimodal Large Language Models (VideoMLLMs) have achieved remarkable progress in both Video-to-Text and Text-to-Video tasks. However, they often suffer from hallucinations, generating content that contradicts the visual input. Existing evaluation methods are limited to one task (V2T) and also fail to assess hallucinations in open-ended, free-form responses. To address this gap, we propose FIFA, a unified FaIthFulness evAluation framework that extracts comprehensive descriptive facts, models their semantic dependencies via a Spatio-Temporal Semantic Dependency Graph, and verifies them using VideoQA models. We further introduce , a tool-based correction framework that revises hallucinated content. Extensive experiments demonstrate that FIFA aligns more closely with human judgment than existing evaluation methods, and that   effectively improves factual consistency in both text and video generation.

Batuhan Nursal, Cassie S. Mitchell

Scientific abstracts and lay summaries serve distinct but critical roles in research communication. Abstracts use technical language for academic audiences, while lay summaries aim to make findings accessible to non-specialists. With the rise of large language models (LLMs), there is increasing interest in automating the generation of both types of summaries—especially in the biomedical domain, where clarity and factual accuracy are essential. This study evaluates the performance of lightweight LLMs (under 8B parameters) in generating biomedical abstracts and lay summaries in a zero-shot setting. We assess outputs across three key dimensions: relevance, readability, and factuality. Additionally, we introduce a novel analysis of the sectional origin and desirability of information—where desirability reflects the utility of content from the reader’s perspective. We further compare human and LLM preferences using an objective ranking task. Our results show that LLM-generated summaries often contain comparable levels of desirable information to gold-standard human references. In several cases, LLM outputs are preferred by human evaluators and occasionally mistaken for human-authored text. These findings demonstrate the potential of lightweight LLMs for scalable, high-quality summarization and suggest their practical use in domains requiring both technical and accessible communication. The codebase for this study is publicly available on GitHub: https://github.com/batuinmetz/Understanding-LLMs-summarization-capabilities

Hanning Zhang, Juntong Song, Juno Zhu, Yuanhao Wu, Tong Zhang, Cheng Niu

Reward Modeling is critical in evaluating and improving the generation of Large Language Models (LLMs). % They are typically trained on high-quality annotated datasets to distinguish between better and worse responses. While numerous recent works have shown its feasibility in improving safety, helpfulness, reasoning, and instruction-following ability, its capability and generalization to open-ended long-context generation is still rarely explored.In this paper, we introduce OpenGenAlign, a framework and a high-quality dataset designed to develop reward models to evaluate and improve hallucination-free, comprehensive, reliable, and efficient open-ended long-context generation. We define four key metrics to assess generation quality and develop an automated pipeline to evaluate the outputs of multiple LLMs across long-context QA, Data-to-Text, and Summarization scenarios using o3, ending up with 33K high-quality preference data with a human agreement rate of 81%. Experimental results first demonstrate that existing reward models perform suboptimally on the held-out benchmark. And Our trained reward model achieves superior performance in the benchmark and effectively improves the generation quality of the policy models using Reinforcement Learning (RL). Additionally, OpenGenAlign could be used for effective guided generation in existing datasets. Furthermore, we demonstrate that the OpenGenAlign could be integrated with reward data from other domains to achieve better performance.

Kangsan Noh, Sanghoun Song

This study investigates whether the grammatical constraints on wanna contraction—a phenomenon traditionally cited as evidence for innate linguistic knowledge—can be learned via BabyLMs, which are designed to reflect cognitively plausible learning conditions. Two datasets were constructed from the CHILDES corpus, varying in embedded verb frequency (high vs. low) and grammaticality, and contrasting grammatical instances (object extraction contexts) with ungrammatical ones (subject extraction contexts) of wanna contractions. Using surprisal as a metric, we evaluated 24 BabyLMs from the 2024 BabyLM Challenge alongside four standard models, including BERT and GPT-2. While the standard models performed with near-perfect consistency, the BabyLMs showed modest but meaningful sensitivity, particularly those trained on larger datasets and tested on high-frequency wanna instances. In particular, only encoder-based BabyLMs captured the grammatical constraint, with babylm24_MLSM exhibiting consistent performance. Nonetheless, our findings provide evidence for limited and conditional learnability of wanna contraction by artificial learners under cognitively realistic input conditions.

EunJeong Hwang, Yuwei Yin, Giuseppe Carenini, Peter West, Vered Shwartz

Theory of Mind (ToM)—an understanding of the mental states of others—is a key aspect of human social intelligence, yet, chatbots and LLM-based social agents do not typically integrate it. In this work, we demonstrate that LLMs that explicitly use ToM get better at dialogue, achieving goals more effectively. After showing that simply prompting models to generate mental states between dialogue turns already provides significant benefit, we further introduce ToMAgent (ToMA), a ToM-focused dialogue agent. ToMA is trained by pairing ToM with dialogue lookahead to produce mental states that are maximally useful for achieving dialogue goals. Experiments on the Sotopia interactive social evaluation benchmark demonstrate the effectiveness of our method over a range of baselines. Extensive analysis shows that ToMA exhibits more strategic, goal-oriented reasoning behaviors, which enable long-horizon adaptation, while maintaining better relationships with their partners. Our results suggest a step forward in integrating ToM for building socially intelligent LLM agents.

Adel Khorramrouz, Sharon Levy

Safety guardrails in large language models (LLMs) are developed to prevent malicious users from generating toxic content at a large scale. However, these measures can inadvertently introduce or reflect new biases, as LLMs may refuse to generate harmful content targeting some demographic groups and not others. We explore this selective refusal bias in LLM guardrails through the lens of refusal rates of targeted individual and intersectional demographic groups, types of LLM responses, and length of generated refusals. Our results show evidence of selective refusal bias across gender, sexual orientation, nationality, and religion attributes. This leads us to investigate additional safety implications via an indirect attack, where we target previously refused groups, and find that Llama 3.1 fails to defend against our attack in roughly 89% of the trials. Our findings emphasize the need for more equitable and robust performance in safety guardrails across demographic groups.

Sibo Zhu, Wenyi WU, Kun Zhou, Stephen Wang, Biwei Huang

The remarkable progress of vision–language models (VLMs) has enabled computer-use agents to interact with computers in a human-like manner. Yet real-world computer-use tasks remain difficult due to long-horizon workflows, diverse interfaces, and frequent intermediate errors. Prior work equips agents with external memory built from large collections of trajectories, but relies on flat retrieval over discrete summaries or continuous embeddings, falling short of the structured organization and self-evolving characteristics of human memory. Inspired by the brain, we propose Hybrid Self-evolving Structured Memory (HyMEM), a graph-based memory that couples discrete high-level symbolic nodes with continuous trajectory embeddings. HyMEM maintains a graph structure to support multi-hop retrieval, self-evolution via node update operations, and on-the-fly working-memory refreshing during inference. Extensive experiments show that HyMEM consistently improves open-source computer-use agents, enabling 7B/8B backbones to match or surpass strong closed-source models; notably, it boosts Qwen2.5-VL-7B by +22.5% and outperforms Gemini2.5-Pro-Vision and GPT-4o.

Xiao Zhang, Qianru Meng, Yongjian Chen, Yumeng Wang, Johan Bos

Many real-world questions appear deceptively simple yet implicitly demand two capabilities: (i) systematic coverage of a bounded knowledge universe and (ii) compositional set-based reasoning over that universe, a phenomenon we term “the tip of the iceberg.” We formalize this challenge through two orthogonal dimensions: knowledge width, the cardinality of the required universe, and reasoning depth, the number of compositional set operations. We introduce KnowledgeBerg, a benchmark of 4,800 multiple-choice questions derived from 1,183 enumeration seeds spanning 10 domains and 17 languages, with universes grounded in authoritative sources to ensure reproducibility. Representative open-source LLMs demonstrate severe limitations, achieving only 5.26–36.88 F1 on universe enumeration and 16.00–44.19 accuracy on knowledge-grounded reasoning. Diagnostic analyses reveal three stages of failure: completeness, or missing knowledge; awareness, or failure to identify requirements; and application, or incorrect reasoning execution. This pattern persists across languages and model scales. Although test-time compute and retrieval augmentation yield measurable gains—up to 4.35 and 3.78 points, respectively—substantial gaps remain, exposing limitations in how current LLMs organize structured knowledge and execute compositional reasoning over bounded domains. The dataset is available at https://huggingface.co/datasets/2npc/KnowledgeBerg

Yifeng He, Ziye Tang, Hao Chen

Information cocoons on social media limit users’ exposure to posts with diverse viewpoints. Modern platforms use stance detection as an important signal in recommendation and ranking pipelines, which can route posts primarily to like-minded audiences and reduce cross-cutting exposure. This restricts the reach of dissenting opinions and hinders constructive discourse. We take the creator’s perspective and investigate how content can be revised to reach beyond existing affinity clusters. We present ContentFuzz, a confidence-guided fuzzing framework that rewrites posts while preserving their human-interpreted intent and induces different machine-inferred stance labels. ContentFuzz aims to route posts beyond their original cocoons. Our method guides a large language model (LLM) to generate meaning-preserving rewrites using confidence feedback from stance detection models. Evaluated on four representative stance detection models across three datasets in two languages, ContentFuzz effectively changes machine-classified stance labels, while maintaining semantic integrity with respect to the original content.

Hanbing Liu, Lang Cao, Yang Li

Large language models (LLMs) acquire most of their knowledge during pretraining, which ties them to a fixed snapshot of the world and makes adaptation to continuously evolving knowledge challenging. As facts, entities, and events change over time, models may experience continuous knowledge drift, resulting not only in outdated predictions but also in temporally inconsistent reasoning. Although existing approaches, such as continual finetuning, knowledge editing, and retrieval-augmented generation (RAG), aim to update or supplement model knowledge, they are rarely evaluated in settings that reflect chronological, evolving, and real-world knowledge evolution. In this work, we introduce a new benchmark of real-world dynamic events, constructed from time-stamped evidence that captures how knowledge evolves over time, which enables systematic evaluation of model adaptation under continuous knowledge drift. The benchmark reveals that most existing methods, including vanilla RAG and several learning-based approaches, struggle under this setting, exposing critical limitations such as catastrophic forgetting and temporal inconsistency. To mitigate these limitations, we propose a time-aware retrieval baseline, Chronos, which progressively organizes retrieved evidence into an Event Evolution Graph to enable more temporally consistent understanding in LLMs without additional training. Overall, this work provides a foundation for analyzing and advancing LLM adaptation to continuous knowledge drift in realistic settings.

Mael Jullien, Andre Freitas, Marco Valentino, Lei Xu

Large language models can produce fluent judgments for clinical natural language inference, yet they frequently fail when the decision requires the correct inferential schema rather than surface matching. We introduce CARENLI, a compartmentalised agentic framework that routes each premise–statement pair to a reasoning family and then applies a specialised solver with explicit verification and targeted refinement. We evaluate on an expanded CTNLI benchmark of 200 instances spanning four reasoning families: Causal Attribution, Compositional Grounding, Epistemic Verification, and Risk State Abstraction. Across four contemporary backbones models, CARENLI improves mean accuracy from about 23% with direct prompting to about 57%, a gain of roughly 34 points, with the largest benefits on structurally demanding reasoning types. These results support compartmentalisation plus verification as a practical route to more reliable and auditable clinical inference.

Yuxiao Li, Alina Fastowski, Efstratios Zaradoukas, Bardh Prenkaj, Gjergji Kasneci

Activation steering has emerged as a powerful tool to shape LLM behaviour without the need for weight updates. While its inherent brittleness and unreliability are well-documented, its safety implications remain underexplored. In this work, we present a systematic safety audit of steering vectors obtained with Contrastive Activation Addition (CAA), a widely used steering approach, under a unified evaluation protocol. We show that steering vectors consistently influence the success rate of jailbreak attacks, with stronger amplification under simple template-based attacks. Across LLM families and sizes, steering the model in specific directions can drastically increase (by up to 57%) or decrease (by up to 50%) its attack success rate (ASR), depending on the targeted behaviour. We attribute this phenomenon to the overlap between the steering vectors and the latent subspace of refusal behaviour. Thus, we offer a mechanistic explanation for this discovery. Together, our findings reveal the previously unobserved origin of this safety gap in LLMs, highlighting a trade-off between controllability and safety. We release our code at https://github.com/yetiiil/analyse-sv-safety.