paperlist.ai

AI 顶会论文

AI 顶会论文库

检索 30+ 个顶会的论文，包括 NeurIPS、ICLR、ICML、CVPR、ACL、AAAI 等。输入关键词筛选，打开任意一篇查看摘要、作者和链接。

arXiv

Representation of syntax in LLMs through the lens of linear distance and similarity-aware entropy

Juan Pablo Vigneaux, Mary Kennedy, Khalil Iskarous, Robert Frank, Matilde Marcolli

Structural probes were introduced by Hewitt and Manning to reconstruct syntactic trees from a neural language model's latent representations. They are evaluated by calculating the proportion of syntactic tree edges correctly reconstructed over an annotated corpus (as measured by undirected unlabeled attachment score). Here, we disaggregate this measure, considering undirected attachment score by label (UASL), which assesses the reconstruction accuracy of each syntactic relation separately, establishing important differences among relations that overlap linguistic distinctions. Moreover, we identify two factors that predict most of UASL's variability across relations: (i) the mean and dispersion of the linear distance (on a log scale) between the related words, and (ii) the diversity (similarity-aware entropy) of the syntactic relation's head. These results, which hold across a range of model sizes and architectures, shed light on the degree of abstraction of the representation of syntax in language models and the dependence of such representation on geometric properties of the embedding space.

arXiv

CEDAR: Automata as Verifiable Interfaces for Language-Guided Embodied Action

Lekai Chen, Alvaro Velasquez, Ashutosh Trivedi

Natural-language tasking of embodied agents is rarely just goal specification: users also impose constraints that must persist while the world changes. Code-generating LLM agents can produce plausible behaviors for such instructions, but their free-form programs provide no stable object to verify, compose with new constraints, or repair from a failing trace. We present CEDAR, a counterexample-guided framework that grounds instructions as regular languages over environment event traces. CEDAR uses a language model for semantic judgments and execution traces for correction, then represents both skills and specifications as deterministic finite automata. This turns constraints into executable finite-state objects: a learned skill can be intersected with a learned sleep at night or stay in this biome specification, yielding a controller that enforces the learned constraint by construction rather than by repeated prompting. In Minecraft, with the same simulator/API observations available to a program-generating baseline, CEDAR maintains temporal and spatial constraints that the baseline fails to preserve and amortizes reuse of learned skills, reducing cumulative LLM queries. These results suggest that regular languages offer a practical verification layer between natural-language instructions and embodied-agent policies.

arXiv

Set-shifting Behavioral Test for Harnessed Agents

Ye Ziwei

What happens to an LLM agent's tool choice when the reliable tool silently changes within an ongoing session? We borrow the notion of set-shifting from cognitive psychology to study how well agents adapt to hidden reliability shifts. Our cognitive test for LLM agents mounts libraries of redundant tools and skills, in which many tools solve the same task but differ in hidden reliability. Using a branching schedule, we shift the reliable tool group in the environment and compare it with a stable control, allowing us to isolate the effect of each shift on the agent's behavior. We conduct our study on a panel of LLMs equipped with harnesses and show that the same set of shifts results in distinct behaviors across models: some latch onto a fixed routine within a few turns, whereas others continue to vary. Less capable models often omit the reliable tool group, while frontier models keep calling it alongside the other groups. We introduce a suite of measures to quantify agent behavior after reliability shifts. While policy prompting substantially alters behavior in some tested models, our findings highlight agents' brittleness when changes occur in indirectly observable context.

arXiv

ProfileFoundry: A Synthetic Person-Object Substrate for Privacy, Memory, and Tool-Use Evaluation in LLM Agent

Sriram Selvam, Anneswa Ghosh

Foundation-model research increasingly needs data about people: user state, personal histories, relationships, contact-like fields, documents, and longitudinal updates. Real user data is difficult to share, perturb, audit, or redistribute responsibly, while independently generated fake fields rarely preserve the cross-field and temporal consistency needed for controlled evaluation. We present ProfileFoundry, a deterministic generator and fixed reference release of 100,000 adult synthetic Person Objects across eight locales. Each object combines a typed current snapshot, household, family, and employer links, snapshot-aligned events, normalized relational views, and generation provenance. The release contains 709,228 events, 40,338 households, 52,491 employers, and 518,564 directed relationship edges. We report evidence in separate categories: selected population-marginal comparisons, per-object invariant checks, release-wide referential and temporal closure, and coincidence/provenance screens. A pilot case study, MatchDesk, uses certified coincidences, typed events, and history truncation to evaluate whether models distinguish corroborated identity evidence from underdetermined matches. ProfileFoundry is not a population-fidelity model, a rendered-text corpus, or a formal privacy mechanism. Instead, it is a responsible synthetic source layer for constructing downstream foundation-model evaluations involving memory, privacy, document understanding, record linkage, and agent state while keeping the synthetic person behind each artifact inspectable.

arXiv

Does Finetuning with Scientific Data Increase Hallucinations? A Multi-domain Factuality Evaluation of LLMs

Raia Abu Ahmad, Nikolas Rauscher, Ekaterina Borisova, Fabio Barth, Georg Rehm, Sebastian Möller

Large language models (LLMs) are increasingly used to communicate and explain scientific concepts, yet their tendency to hallucinate poses significant risks in this high stakes use-case. Prior scientific hallucination evaluation work remains largely restricted to the biomedical domain, treats hallucination as a binary task, and has not examined the growing family of scientifically fine-tuned LLMs. We address these gaps with SciFactCheck, a benchmark of 2,500 prompts across five scientific domains, paired with a modular evaluation framework targeting three factuality hallucination types: unverifiability, overclaim, and attribution. Using a controlled minimal-pairing design, we evaluate 18 LLMs by comparing each scientifically fine-tuned model against its general-purpose base. Our results indicate that 1. Scientifically fine-tuned models exhibit degraded factual reliability across all hallucination types and scientific domains, and 2. Fine-tuned models are internally less confident yet linguistically more assertive. A human pilot study further reveals that current fact-checking tools show only modest agreement with expert judgments on scientific content, and that defining scientifically check-worthy claims remains contested even among human annotators. Our findings fundamentally challenge current methods of domain-specific fine-tuning for factuality and call for developing improved verification infrastructure for scientific content.

arXiv

Closing the Operational Gap in Semantic Caching

Aditeya Baral, Radoslav Ralev, Iliya Sotirov Zhechev, Srijith Rajamohan, Jen Agarwal

Semantic caching cuts LLM inference costs by serving a cached response to semantically similar queries. Standard practice evaluates these systems using PR-AUC, a metric that only measures how well scores rank and ignores whether they are usable at a fixed threshold. We show this mismatch leads to systematically poor deployment choices, as models with the highest PR-AUC are often the worst in operation. We introduce Precision--Cache Hit Ratio (P-CHR) AUC, a cache-aware metric that measures precision across cache utilization levels, and Operational Retention Rate (ORR), which captures how much offline ranking quality survives at deployment. We decompose the operational gap between offline and deployed quality into a recoverable threshold-utility component and an irreducible structural component fixed by the dataset's positive rate. Our experiments show that the threshold-utility gap is governed by the training objective rather than data scale, and yields only to re-normalizing scores over the candidate pool or changing the training objective. Ultimately, model selection for semantic caching is a threshold-utility problem, not a ranking one, and measuring it is the first step to closing the gap.

arXiv

Securing Multi-Agent GIS Systems: Risk Evaluation and Prompt Hardening Optimization

Kyle Gao, Pranavi Kotta, Linlin Xu, Jonathan Li, David A. Clausi

Agentic systems are increasingly integrated with geographic information systems (GIS), where multi-agent coordination enables complex conversational and spatial analysis but introduces security risks. This work presents a security-oriented framework for risk identification, evaluation, and mitigation in a multi-agent GIS system while maintaining adaptability to broader agentic architectures. We test the agentic system of a commercial geospatial partner while developing a modular state-machine-based orchestration framework that abstracts agent behavior into reusable components. We evaluate robustness using a red-teaming framework with an adaptive attacker LLM and a deterministic judge that produces binary outcomes with supporting rationales across multi-turn attacks. We further improve resilience with a prompt optimization framework that treats prompts as structured signatures and injects adversarial demonstrations, enabling systematic security improvements without degrading task performance.

arXiv

TokenPilot: Cache-Efficient Context Management for LLM Agents

Buqiang Xu, Zirui Xue, Dianmou Chen, Chenyang Fu, Chiyu Wu, Caiying Huang, Chen Jiang, Jizhan Fang, Xinle Deng, Yijun Chen, Yunzhi Yao, Xuehai Wang, Jin Shang, Gong Yu, Ningyu Zhang

As LLM agents are deployed in long-horizon sessions, context accumulation drives up inference costs. Existing approaches utilize text pruning or dynamic memory eviction to minimize token footprints; however, their unconstrained sequence mutations alter layouts, introducing prefix mismatches and cache invalidation. This reveals a critical trade-off between text sparsity and prompt cache continuity. To address this, we present TokenPilot, a dual-granularity context management framework. Globally, Ingestion-Aware Compaction acts as a framework harness to stabilize prompt prefixes and eliminate open-world environmental noise at the ingestion gate. Locally, Lifecycle-Aware Eviction monitors the ongoing residual utility of context segments, enforcing a conservative batch-turn schedule to offload content segments only when task relevance expires. Experiments on PinchBench and Claw-Eval under both isolated and continuous modes demonstrate that TokenPilot reduces costs by 61% and 56% in isolated mode, and 61% and 87% in continuous mode, while maintaining competitive performance compared to prior systems. TokenPilot has been integrated into LightRSI at https://github.com/zjunlp/RSI.

arXiv

MemoryCard: Topic-Aware Multi-Modal Clue Compression for Long-Video Question Answering

Qing Yang, Pengcheng Huang, Xinze Li, Zhenghao Liu, Yukun Yan, Yu Gu, Ge Yu, Gang Li, Maosong Sun

Long-video question answering remains challenging for Vision-Language Models (VLMs), as answer-relevant evidence is often sparse, transient, and temporally dispersed across lengthy video contexts. Existing frame-centric approaches improve efficiency through uniform sampling, query-aware frame selection, visual-token compression, and adaptive resolution strategies. However, they still rely on isolated and fragmented frames as the fundamental evidence units, limiting VLMs' ability to effectively capture coherent event-level semantics. To address this limitation, we propose MemoryCard, a video-memory-based augmentation framework that organizes long videos into self-contained Memory Cards. Specifically, MemoryCard first performs a self-reading process over videos and aligned utterances to segment the video into semantically coherent units, each corresponding to a distinct topic or event. For each unit, it generates an event-level video gist and selects representative visual moments, which are then rendered into unified Memory Cards for retrieval and question answering. Experimental results demonstrate that MemoryCard consistently improves long-video QA performance under comparable visual-token budgets, achieving up to a 21.8% relative improvement in accuracy. All code is available at https://github.com/NEUIR/MemoryCard.

arXiv

Self-Evaluation Is Already There: Eliciting Latent Judge Calibration in Base LLMs with Minimal Data

XiuYu Zhang, Yi Shan, Junfeng Fang, Zhenkai Liang

Large language models are increasingly evaluated by other models, raising a natural question: can a model predict how a judge will score its own output? We find that the ability is largely present before any targeted training: prompted few-shot, a base model already predicts an external judge's multi-attribute quality scores on open-ended responses well above chance across three benchmarks. We introduce Self-Evaluation Elicitation (SEE), a method that surfaces this latent ability through a short cycle comprising a calibration-coupled reinforcement learning phase that improves the answer and predicts the judge, followed by a masked distillation phase that sharpens the prediction while leaving the answer untouched. From 160 unique examples, roughly 31x fewer than a reinforcement learning baseline, SEE improves held-out calibration across three benchmarks while preserving answer quality. The elicited self-evaluation is sharply localized within the model's own token distribution and stable across judges it was never trained against, indicating a transferable notion of quality rather than a single judge's preference. These results reframe judge-aligned self-evaluation as a problem of elicitation rather than acquisition.

arXiv

RealClawBench: Live OpenClaw Benchmarks from Real Developer-Agent Sessions

Zongwei Lv, Yaoming Li, Zhewen Tan, Yilun Yao, Yuxuan Tian, Lin Sun, Xiangzheng Zhang, Weihong Lin, Tong Yang, Guangxiang Zhao

Agent benchmarks should reflect what users actually ask deployed agents to do, yet existing benchmarks often miss key realism properties of real developer-agent sessions. We introduce RealClawBench, a live benchmark framework built from real OpenClaw sessions to capture the distribution, diversity, and real-world difficulty of deployed agent use. Real user requests are challenging to benchmark because they often depend on local execution environments, involve implicit or underspecified intent, and require nontrivial verification. RealClawBench addresses these challenges with two core mechanisms: reconstructed execution environments and deterministic verifiable scorers, which together convert real sessions into reproducible, automatically scored tasks. The resulting release contains 281 executable tasks sampled from a much larger real-session pool while preserving the source distribution, with maximum final-vs-source Jensen-Shannon divergence of 0.0448. Evaluating 14 contemporary models shows that the best system solves only 65.8% of tasks, revealing substantial headroom on realistic developer-agent workloads. By turning real deployed sessions into controlled evaluation instances, RealClawBench provides a practical path toward benchmarks that better measure agent capability in actual use. Code is available at:https://anonymous.4open.science/r/real-claw-bench-582B.

arXiv

DiffuSent: Towards a Unified Diffusion Framework for Aspect-Based Sentiment Analysis

Shu Long, Yanglei Gan, Xuchuan Zhou

Aspect-Based Sentiment Analysis (ABSA) encompasses seven distinct subtasks, each focusing on different extracted elements. Despite the proven success of generative models in unified aspect sentiment analysis, existing approaches often rely on auto-regressive token-by-token generation without grasping the whole information of the aspect and opinion terms, resulting in boundary insensitivity, particularly in context of multi-word aspect and opinion terms. To address these issues, we present DiffuSent, a non-auto-regressive diffusion framework that systematically formulates all ABSA subtasks as boundary denoising diffusion processes, progressively refining boundaries over noisy states. Furthermore, we introduce a contrastive denoising training strategy which effectively address duplicate predictions with subtle variations introduced by diffusion process. Extensive experiments across 28 settings (7 subtasks x 4 datasets) demonstrate that DiffuSent achieves delivers consistent improvements over the strongest generative and span-based systems. DiffuSent exhibits notable gains on multi-word triplets, achieving an average improvement of +2.48 F1, and maintains robust extraction accuracy in sentences containing multiple sentiment triplets. Moreover, the non-auto-regressive decoding enables substantial efficiency benefits, reaching up to 181 times faster inference than auto-regressive generative baselines

arXiv

Auditing LLM Benchmarks with Item Response Theory

Sander Land, Daniel M. Bikel

LLM benchmark labels are frozen at release and silently propagated into downstream benchmarks, errors and all. We introduce an Item Response Theory-based indicator that surfaces likely mislabels at 95% precision in the top 200 examples across seven preference and multiple-choice benchmarks using responses from 114 models, outperforming a supervised classifier. We trace these errors to mechanical labeling heuristics, upstream annotation mistakes inherited unchanged from source datasets, and fundamentally ambiguous items without a defensible single label. The same model fit reveals that reward models specialize in stylistic preference rather than factual knowledge, and identifies one frontier reward model that agrees with detected mislabels at 78% accuracy versus 38% for its peers, consistent with benchmark contamination or benchmark-specific over-optimization.

arXiv

LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis

Kewei Xu, Xiaoben Lu, Shuofei Qiao, Zihan Ding, Haoming Xu, Lei Liang, Ningyu Zhang

Real-world data analysis is inherently iterative, yet existing benchmarks mostly evaluate isolated or short interactive tasks, leaving agents' ability to track evolving analytical context over long horizons untested. We introduce LongDS, a benchmark for long-horizon, multi-turn data analysis where agents must maintain, update, restore, and compose evolving analytical states. LongDS comprises 68 tasks constructed from real-world Kaggle notebooks, spanning 2,225 turns across six domains including Geoscience, Business, and Education. Tasks are designed around state-evolution patterns (e.g., counterfactual perturbation, rollback, multi-state composition), with an average dependency span of 11.3 turns. Evaluating five state-of-the-art models, we find that the best model reaches only 48.45% average accuracy, performance drops nearly 47 points from early to late turns, and long-horizon errors account for 52%--69% of failures. Further analysis shows that additional agent steps do not necessarily improve performance, suggesting that the key bottleneck is maintaining a correct analytical state rather than increasing interaction budget. We release LongDS to support research on reliable long-horizon agentic data analysis. Code and data are released at https://github.com/zjunlp/DataMind.

arXiv

Human Label Variation as Stable Signal: Learning Annotator-Specific Explanation Behavior via Cross-Annotator Preference Optimization

Beiduo Chen, Pingjun Hong, Ziyun Zhang, Benjamin Roth, Anna Korhonen, Barbara Plank

Free-text explanations extend human label variation (HLV) beyond label disagreement by revealing the reasoning and preferences behind annotators' decisions. We study whether large language models (LLMs) can learn and reproduce such annotator-specific label-explanation behavior. Using two sentence-pair tasks with four annotators each -- natural language inference and paraphrase judgment -- we first analyze whether annotators exhibit stable individual patterns. We find that such patterns are weak at the single-annotation level due to strong input-content effects, but become detectable after input-content reduction and annotator-level aggregation. We then compare prompting and supervised fine-tuning (SFT) baselines and propose cross-annotator preference optimization (CAPO), which contrasts a target annotator's response with other valid but less target-specific annotations for the same input. Experiments show that prompting is limited and unstable, SFT better captures annotator-specific behavior, and CAPO further improves aggregation-aware imitation and judge-based attribution while preserving target-specific reasoning patterns under human validation. Overall, our results show that HLV can be learned as annotator-specific label-explanation behavior, suggesting a path toward scalable explanation-based annotation grounded in annotator histories rather than labels alone.

arXiv

A Wolf in Sheep's Clothing: Targeted Routing Hijacking in Federated RAG

Junjie Mu, Qiongxiu Li

Federated Retrieval-Augmented Generation (FedRAG) is attractive for privacy-sensitive applications because full local corpora remain on clients. As a result, routing must rely on client-provided semantic profiles, creating a new opportunity for manipulation. We introduce Routing Hijacking, a routing-stage attack in which a malicious client forges its profile to attract target queries despite having irrelevant underlying data. We show that this vulnerability is severe. Across three representative FedRAG routing architectures, Routing Hijacking consistently misroutes target queries and leads to downstream disruptions and failures, including missing evidence, poisoning, incorrect answers, and hallucinations. In a controlled MedQA-USMLE stress test, we further show that poisoned retrieved evidence can mislead models across scales, leading to incorrect answers, hallucinations, and sycophantic failures. Existing defenses do not close this gap: encrypted routing preserves the exploited ranking, and Byzantine-robust Federated Learning (FL) rules transfer poorly to heterogeneous routing profiles. To address this gap, we propose a trust-aware post-routing framework that reweights clients using returned-evidence feedback, including retrieval relevance, profile consistency, and cross-client agreement; online experiments show that it suppresses persistent hijacking over recurring queries and transfers to a learned neural router. Our findings establish routing integrity as a security challenge in FedRAG and highlight the need for stronger defenses for secure federated retrieval.

arXiv

SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces

Chang Jin, An Wang, Zeming Wei, Kai Wang, Biaojie Zeng, Qiaosheng Zhang, Chao Yang, Jingjing Qu, Xia Hu, Xingcheng Xu

Reusable skills are becoming a common interface for extending large language model agents, packaging procedural guidance with access to files, tools, memory, and execution environments. However, this modularity introduces attack surfaces that are largely missed by existing safety evaluations: even when the user request is benign, unsafe influence may reside in skill guidance, local artifacts, or execution-environment files that steer the agent toward unsafe actions. We present SkillSafetyBench, a runnable benchmark for evaluating such skill-facing safety failures. SkillSafetyBench includes 155 adversarial cases across 47 tasks, 6 risk domains, and 30 safety categories, each evaluated with a case-specific rule-based verifier. Experiments with multiple CLI agents and model backends show that non-user attacks can consistently induce unsafe behavior, with distinct failure patterns across domains, attack methods, and scaffold-model pairings. Our findings suggest that agent safety depends not only on model-level alignment, but also on how agents interpret skills, trust workflow context, and act through executable environments. The complete benchmark is available at https://github.com/AI45Lab/skill-safety-bench.

arXiv

Why are all LLMs Obsessed with Japanese Culture? On the Hidden Cultural and Regional Biases of LLMs

Joseba Fernandez de Landa, Carla Perez-Almendros, Jose Camacho-Collados

LLMs have limitations when it comes to cultural coverage and competence, and in some cases, show specific cultural biases. Although prior studies have examined the cultural capabilities of LLMs, none have specifically investigated their regional preferences in generic culture-related questions. In this work, we propose a new dataset based on a comprehensive taxonomy of Culture-Related Open Questions (CROQ), with questions available in 24 languages. We evaluate LLMs by prompting them to answer questions from CROQ and provide a sample location. The results show that, contrary to previous cultural bias work, LLMs show a clear tendency towards countries such as Japan in their answers. Moreover, our results show that when prompting in languages such as English or other high-resource ones, LLMs tend to provide more diverse outputs. Low-resource languages, on the other hand, show more inclinations towards answering questions highlighting countries for which the input language is an official language. Finally, we also investigate at which point of LLM training this cultural bias emerges, with our results suggesting that the first clear signs appear after supervised fine-tuning, and not during pre-training. Dataset available at https://huggingface.co/datasets/HiTZ/CROQ

arXiv

Select, Label, Evaluate: Active Testing in NLP

Antonio Purificato, Maria Sofia Bucarelli, Andrea Bacciu, Fabrizio Silvestri, Amin Mantrach

Human annotation cost and time remain significant bottlenecks in Natural Language Processing (NLP), with test data annotation being particularly expensive due to the stringent requirement for low-error and high-quality labels necessary for reliable model evaluation. Traditional approaches require annotating entire test sets, leading to substantial resource requirements. Active Testing is a framework that selects the most informative test samples for annotation. Given a labeling budget, it aims to choose the subset that best estimates model performance while minimizing cost and human effort. In this work, we formalize Active Testing in NLP and we conduct an extensive benchmarking of existing approaches across 18 datasets and 4 embedding strategies spanning 4 different NLP tasks. The experiments show annotation reductions of up to 95%, with performance estimation accuracy difference from the full test set within 1%. Our analysis reveals variations in method effectiveness across different data characteristics and task types, with no single approach emerging as universally superior. Lastly, to address the limitation of requiring a predefined annotation budget in existing sample selection strategies, we introduce an adaptive stopping criterion that automatically determines the optimal number of samples. We release our code at https://github.com/amazon-science/NLPActiveTesting.

arXiv

Large Reasoning Models Struggle to Transfer Parametric Knowledge Across Scripts

Lucas Bandarkar, Alan Ansell, Trevor Cohn

In this work, we analyze shortcomings in cross-lingual knowledge transfer in large, modern reasoning LLMs. We demonstrate that the perceived gap in knowledge transfer is primarily a script barrier. First, we conduct an observational data analysis on the performance of thinking models on two datasets with local knowledge from around the world, ECLeKTic and MultiLoKo. Our regression analysis shows that script match - not language or family - is the primary predictor of knowledge transfer failure once model capability and question difficulty are accounted for. We further this finding by providing the LLMs with the key entities of the questions in their source language and find that this disproportionately improves cross-script questions. We then posit that these LLMs could be reasoning better at test-time. To evaluate this, we develop a synthetic generation pipeline to design SFT samples to encourage the model to better reason about transliteration ambiguities when trying to fetch parametric knowledge at inference-time. We show that teaching two models to reason better reduces the cross-script transfer gap. As a result, we conclude that there is potential to improve cross-lingual parametric knowledge transfer during post-training.

继续浏览

更多 AI 顶会论文

30+ 个顶会，按会议、年份和主题浏览。

浏览全部会议

进入任一会议和年份，查看完整论文列表。

全部会议 →

搜索论文

按标题、作者或关键词，在 21 万+ 篇论文里搜索。

搜索论文 →