跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 05:07 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 05:38 — 2026-11-09 05:38（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-09 05:07最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

17,100 已收录论文14,661 AI 相关4,057 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 17 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 05:05（北京时间）
新论文 · v1arXiv:2611.08094

PersonaAgent: Retrieval-Augmented Transaction Anomaly Scoring with Refreshable Multi-Entity Persona Memory

Zhengyu Fang, Liang Wang, Yingtong Dou, Yuzhong Chen, Shubham Jain, Junpeng Wang, Xiran Fan, Menghai Pan 等 11 位作者

原文摘要

In large-scale payment networks, entities (card, merchant, etc.) and their interactions play a key role in transaction anomaly detection. However, transaction patterns between different entities usually change more frequently than the production model refresh schedule. Meanwhile, entity embedding tables suffer from high-cardinality and sparse interaction issues. To resolve the above challenges, we present PersonaAgent, an agentic transaction anomaly detection framework which represents the latest entity behavior signals as personas and saves them in a refreshable memory. Offline, a weekly scheduled batch job is used to extract the latest behavior signals and update them in the memory. At inference time, a lightweight adapter retrieves the corresponding entity behavior signals of each transaction from memory and uses them to augment the base anomaly classifier's scoring. Through comprehensive benchmarking with different anomaly detection models at Visa, PersonaAgent is able to score transactions efficiently (a 1,000-transaction CPU batch in 1-2 ms), lifting the PR-AUC by 0.65-6.58% and the production business metric by 8.93-14.24% relatively in deployment.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.13033

DenseReward: Dense Reward Learning via Failure Synthesis for Robotic Manipulation

Yu Fang, Wanxi Dong, Jiaqi Liu, Yue Yang, Mingxiao Huo, Yao Mu, Huaxiu Yao, Li Erran Li 等 10 位作者

原文摘要

Reinforcement learning holds great promise for improving robot policies beyond the limits of imitation learning. However, its practical adoption remains bottlenecked by the lack of reliable vision-language reward models that provide dense and informative feedback. Two key challenges remain: acquiring diverse failure data at scale and obtaining fine-grained reward signals beyond sparse trajectory-level success labels. Existing approaches reuse successful trajectories to construct negative or suboptimal examples through trajectory truncation, instruction relabeling, or trajectory comparisons, without generating new trajectories where physical interaction failures such as collisions, missed grasps, object drops, and recovery actually occur. Meanwhile, many existing reward models predict sparse binary or trajectory-level rewards, which provide limited guidance for efficient policy optimization. We introduce DenseReward, a dense robotic reward model that addresses both challenges. To train DenseReward, we develop an automated failure data generation pipeline that synthesizes physically realistic failure trajectories in simulation without manual annotation, covering diverse failure modes such as collisions, missed grasps, object drops, and recovery behaviors. DenseReward predicts dense frame-level reward scores from visual observations and language instructions, enabling fine-grained estimation of task progress throughout an episode. Experiments show that DenseReward outperforms general-purpose VLMs and existing robotic reward models in dense reward prediction across both simulated and real-world manipulation. We further demonstrate that DenseReward provides effective reward guidance for downstream model predictive control and reinforcement learning.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.17659

When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAs

Yu Fang, Yuchun Feng, Dong Jing, Jiaqi Liu, Yue Yang, Zhenyu Wei, Daniel Szafir, Mingyu Ding

原文摘要

Vision-Language-Action models (VLAs) promise to ground language instructions in robot control, yet in practice often fail to follow language faithfully. When presented with instructions that lack strong scene-specific supervision, VLAs suffer from counterfactual failures: they act based on vision shortcuts induced by dataset biases, repeatedly executing well-learned behaviors and selecting objects frequently seen during training regardless of language intent. To support systematic study, we introduce LIBERO-CF, the first counterfactual benchmark for VLAs that evaluates language following capability by assigning alternative, feasible task instructions under the same LIBERO scene layouts. Our evaluation reveals that counterfactual failures are prevalent yet underexplored across state-of-the-art VLAs. To mitigate these failures, we propose Counterfactual Action Guidance (CAG), a simple yet effective dual-branch inference scheme that explicitly strengthens language conditioning in VLAs. CAG combines a standard VLA policy with a parallel language-unconditioned branch, amplifying the difference between their action predictions induced by language instructions. This design reduces reliance on vision shortcuts, improves robustness on counterfactual tasks, and requires neither additional demonstrations nor modifications to the base VLA architecture or its pretrained weights. Extensive experiments demonstrate consistent improvements across diverse VLAs. On LIBERO-CF, our training-free variant, TF-CAG, improves $π_{0.5}$ by 9.7% in language grounding and 3.6% in task success. When using a separate Vision-Action (VA) module, VA-CAG achieves larger gains of 15.5% and 8.5%, respectively. In real-world evaluations, VA-CAG improves language grounding by 9.4% and task success by 17.2% on average.

cs.CV · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06131

ModalSearcher: Weaving Visual Evidence into Autonomous Cross-Modal Deep Search

Zhihan Yin, Ruyi Li, Chengyu Fang, Yifeng Yao, Nonghai Zhang, Pengfei Xiong, Terry Zhang, Huishuai Zhang 等 9 位作者

原文摘要

Static and incomplete parametric knowledge limits the performance of multimodal large language models on novel-knowledge and knowledge-intensive tasks, especially those requiring multi-hop evidence acquisition. Existing multimodal agentic search methods often fix visual evidence at the input or a predefined trajectory position, making it difficult for agents to select search modalities as their information needs evolve and to handle complex real-world queries. We define this capability as autonomous cross-modal search: an agent chooses among direct reasoning, text-to-text search, text-to-image search, and reverse-image search, actively introduces visual evidence when appropriate, and switches between and integrates modalities across multiple hops. We propose ModalSearch-Pipeline, a scalable procedure for constructing an interleaved multimodal knowledge graph. It samples paths with diverse depths and modality compositions and uses backward question construction to obscure entity names and image targets that would expose reasoning shortcuts while retaining necessary disambiguating clues, yielding text-only, image-initialized, and arbitrarily interleaved multi-hop problems. We train the ModalSearcher Agent with supervised fine-tuning and reinforcement learning in a live Web environment, and construct ModalSearch-Bench. Experiments show that ModalSearcher-8B improves average accuracy by 16.2 points over Qwen3-VL-8B under the same agentic workflow across five multimodal knowledge-intensive QA benchmarks, with consistent gains on independently constructed active visual-search benchmarks.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05636

Route to Remember: Adaptive Memory Selection for LLM Agents

Zeyu Fang, Jun Yin, Yongsheng Mei, Xu Han, Chaitali Joshi, Zhongkai Sun, Jie Hao, Bin Guo 等 11 位作者

原文摘要

The memory of production agents is increasingly becoming a bottleneck and is built almost exclusively from text: key points are extracted from out-of-limit context and retrieved into context at query time. Therefore, every new query incurs an additional cost that grows with the accumulated history. Weight memory is a complementary alternative that internalizes knowledge into model parameters and answers with no context at all, and has recently proven effective in self-evolving agents for internalizing skills and behaviors. However, its application in episodic and semantic memory, such as user-specific facts, remains comparatively unexplored, and a gap remains between earlier attempts at weight memory and text-based systems regarding recall performance. We study how to make weight memory competitive as a long-term factual store by applying on-policy self-distillation (OPSD). It trains a context-free student from a teacher, which is the same model conditioned on the user's memory, together with a verify-then-regenerate router that lets weight and text memory each cover the queries they handle best. On the HaluMem benchmark, OPSD matches or surpasses strong text-memory baselines, including full-context prompting and retrieval systems, while reading fewer tokens per query. We further conduct an extensive study that characterizes the behavior of weight memory and analyzes how different training recipes affect its performance. As agent harnesses move toward persistent, multi-session deployments, these results position weight memory as a practical, low-cost component of agent memory and provide insights into feasible training and evaluation protocols for combining it with retrieval.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05124

The Right Source Is Not Enough: Understanding History Interference in Speech-LLM Memory

HongJin Song, Weiqiao Shan, Runwu Shi, Yifei Wu, Yujin Wang, Jiale Luo, Jiasheng Kuang, Xinyu Yang 等 14 位作者

原文摘要

Speech large language models retain audio history to support multi-turn conversations. Yet remembering an event does not ensure that its information is used only when relevant. We investigate why irrelevant historical audio changes answers even when the queried event remains represented. Controlled experiments on MOSS-Audio and MiMo-Audio show that historical values direct errors toward specific competing answers, beyond a generic effect of context length. Causal interventions distinguish two paths. In open-ended question answering, most history-value errors disappear when subsequent computation cannot directly access the irrelevant source. In multiple-choice answering, many errors persist: early historical influence is carried by question-candidate states even after direct source access is blocked. Low-dimensional interventions further separate source-role information from answer-value information. Their effects peak at different depths, and changing the source-role signal does not eliminate the causal influence of competing values. On naturally occurring errors, strengthening the queried role and counteracting the historical value each improve answers; their joint intervention gives the greatest recovery. These findings support a failure of downstream evidence use beyond source identification alone: source-role information can influence a decision without exclusively controlling which historical values affect it. Reliable conversational memory therefore requires not only retention and retrieval, but also control over how retained information enters answer computation.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02526

INTERACT: Learning Interaction-Aware World Dynamics from Driving Videos for Autonomous Driving

Zhan Chen, Songyan Zhang, Wenhui Huang, Zirui Li, Zhidong Wang, Qihang Huang, Shiyu Fang, Chen Lv

原文摘要

Safe autonomous driving requires more than recognizing the current scene: the ego vehicle must anticipate how surrounding traffic participants will evolve under its own motion. However, existing end-to-end driving models typically encode scenes into dense visual or BEV features, leaving object-level interactions implicit. We propose (INTERACT INTERaction-aware Action-Conditioned Trajectory learning), a three-stage framework that learns a slot-based object-centric world model from unlabeled driving videos and transfers it to trajectory planning. INTERACT first learns recurrent slots that group dense visual features into temporally structured scene-entity representations without object annotations. It then infers latent ego actions from slot context and video transitions, and uses them to condition future slot prediction, capturing how ego motion and surrounding entities co-evolve. Finally, the learned slots, latent actions, and future slot predictions are distilled into a trajectory planner to guide trajectory generation and selection. Extensive experiments on NAVSIM and nuScenes validate the effectiveness of INTERACT. In particular, it achieves state-of-the-art performance on NAVSIM, with improvements in safety-critical collision metrics.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01974

MUPA${}^2$S: Multimodal Unified Perception with Asymmetric Attention for Stress Assessment

Stefanos Gkikas, Thomas Kassiotis, Yu Fang, Christian Arzate Cruz, Miao Cheng, Zongyi Jiang, Zacharias Kamarianakis, Houshyar Asadi 等 11 位作者

原文摘要

Stress is a leading contributor to long-term physical and mental health decline. The automatic assessment of stress is a promising approach for continuous monitoring and mitigating human biases. However, the development of automated systems remains challenging due to the heterogeneity of physiological and behavioral signals. This paper presents MUPA${}^2$S, a multimodal framework for automatic stress assessment that combines facial video and ECG signals within a unified perception architecture. Both modalities are mapped into a shared token representation without modality-specific components, and processed through asymmetric attention comprising segment-local cross-attention and global self-attention across segment states. Experiments on a newly collected 58-subject stress dataset, evaluated under a stratified subject-level protocol, show that facial video achieves 69.44% test accuracy, while ECG-only performance remains close to chance under the proposed representation. Unified Video-ECG fusion achieves a test accuracy of 69.58% at approximately half the number of parameters of feature-level fusion, with negligible additional computational cost. Feature-level fusion does not exceed the video-only baseline, while unified input-level integration provides a parameter-efficient mechanism for jointly processing the two modalities.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.40096

Reward-Adaptive Co-Evolution of Policy and Rubric

Yizhu Chen, Jianguang Jiang, Jiameng Huang, Chuyu Fang, Bojun Zhang, Zhenyu Jiao, Xing Yuan, Tong Lin

原文摘要

Rubric-based rewards provide fine-grained, interpretable supervision for open-ended reinforcement learning, where holistic scalar rewards struggle to capture multidimensional response quality. Static rubrics can lose discriminative power as the policy distribution evolves, while existing policy--rubric co-evolution methods rely on globally prescribed update schedules that ignore heterogeneous reward informativeness. We introduce RACE, a Reward-Adaptive Co-Evolution framework. At the group level, per-rollout-group training-signal routing classifies groups as informative, diversity-collapsed, or rubric-failed, updating the policy only with informative groups while caching rubric failures. At the phase level, event-triggered phase switching enters rubric optimization upon persistent reward saturation and returns when rubric-reward improvement plateaus. Rubric phases train the generator on cached pairs using a frozen judge and a scale-normalized pairwise-margin reward. Across both levels, online threshold adaptation adjusts routing and switching thresholds through proportional control. Under a unified evaluation protocol, RACE achieves the highest average performance and outperforms the strongest fixed-alternation baseline on all eight tasks, while improving rubric discrimination.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.11194

OmniDex: Scaling Dexterous Hand Grasping to Diverse Cluttered Scenes

Naiyu Fang, Zhongjin Luo, Yuxin Mo, Siyuan Huang, Jianbo Liu, Yufei Liu, Zheyuan Zhou, Chenkai Jin 等 10 位作者

原文摘要

Dexterous grasping is the foundational primitive in embodied AI, demanding massive data to train robust models. As real-world data collection is expensive, simulation has become the mainstream paradigm. Yet, while cluttered scenes best reflect real-world applications, learning to grasp within them is bottlenecked by a critical scarcity of large-scale data. To resolve this, we curate high-quality 3D objects and supporting bases, proposing a scalable seed-and-filter strategy that bypasses sluggish scene-level optimization. This yields an unprecedented benchmark comprising over 2.6 million scenes and 0.4B scene-specific grasp ground truths, featuring diverse realistic layouts paired with rich semantic and geometric observations. Furthermore, we introduce the OmniDex model to overcome the grasp multimodality and last-millimeter precision errors plaguing current generative models. By coupling Soft Winner-Takes-All learning with human-inspired physical constraints during training, and utilizing physics-driven ranking, our approach achieves robust dexterous grasping without the latency of post-optimization. Experimental results show that OmniDex model achieves state-of-the-art performance and strong generalization across diverse scenes, views, and unseen objects.

cs.RO · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.22688

DIP-CAD: A Design-Intent-Preserving Agent Harness for Parametric CAD Modeling

Xi Cheng, Chenxi Zhai, Hang Cheng, Mingyu Fan, Pingfa Feng, Long Zeng

原文摘要

Parametric CAD modeling requires not only matching the target shape, but also preserving design intent under parameter edits. However, most existing methods focus on improving static shape generation accuracy, while the dependencies that govern later edits are often overlooked. To tackle this issue, we present DIP-CAD, a design-intent-preserving agent harness for generating parametric CAD models from images. DIP-CAD combines vision-language model reasoning with CAD kernel operations to establish dependencies that encode the design intent. In parametric CAD, these dependencies are mainly established through geometry references in modeling commands and constraints in parametric sketches. At the command level, ID-based explicit geometry reference binds modeling commands to selected faces, edges, or vertices. At the sketch level, a local-coordinate bridge ensures accurate sketch placement, providing the basis for correctly establishing sketch constraints. Constraints among sketch primitives and constraints to external projected geometry further preserve both internal sketch relationships and dependencies on existing geometry. To provide a more comprehensive data foundation for parametric CAD modeling tasks, we introduce the Geometry Explicit Reference Dataset (GERD), whose structured data format links stepwise modeling commands to intermediate CAD models through explicit geometry references. On GERD-EVL and a DeepCAD test subset, DIP-CAD improves mIoU for static model generation by 11.1% and 5.6%, respectively. In parameter-editing evaluations, the corresponding mIoU improvements are 7.0% and 4.2%. Case studies further demonstrate how parameter edits drive shape updates while preserving design intent.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36108

Log-To-Leak: Prompt Injection Attacks on Tool-Using LLM Agents via the Model Context Protocol

Yuepeng Hu, Chongyu Fan, Sirat Samyoun, Jian Du

原文摘要

LLM agents increasingly access external tools through the Model Context Protocol (MCP), but the natural-language metadata used to describe those tools creates a prompt-injection surface. Within this established tool-poisoning surface, we study Log-To-Leak, an additive post-hoc logging attack that induces a separate attacker-controlled call after the final legitimate call. Its payload targets the user query, MCP server name, server response, and agent response. We operationalize the injected directive through Trigger, Tool Binding, Justification, and Pressure, and separately measure call success, payload fidelity, and preservation of legitimate behavior. We evaluate five MCP servers and four LLM agents using five metrics spanning effectiveness, utility, and efficiency. Across 18 model-server pairs with valid tool execution, Log-To-Leak achieves an attack success rate (ASR) of 62.64-100% and conditional logging accuracy (LA) of 76.55-95.64%; 16 pairs have absolute target-task completion changes of at most 6.63 percentage points. Three evaluated defenses leave residual ASR above 55% on GitHub MCP with GPT-4o, while an instruction detector flags 85.53% of benign descriptions. These results show that successful task completion can coexist with unauthorized post-hoc disclosure and motivate host-controlled authorization for secondary tool calls.

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35138HF 社区推荐

Co-Design Bench: Multimodal Collaborative Coding Evaluation for Agentic Models

Xilin Wei, Shengyuan Ding, Xinyu Fang, Tiancheng Gu, Yuchi Wang, Zhixun Li, Ziyu Liu, Yuhang Zang 等 16 位作者

原文摘要

Evaluating human-AI co-design requires testing whether coding agents can translate real users' multimodal requests into working application revisions. We introduce Co-Design Bench, a reference-free benchmark of 273 tasks curated from 37,463 deduplicated queries across 26,314 real user coding sessions. Its two tracks, Multimodal Editing (ME) and Repository Editing (RE), cover localized edits with optional image, audio, video, or document inputs and coordinated repository revisions. Tasks span three capability dimensions: Grounded Understanding, UI Transformation, and Functional Implementation. The tasks pair normalized requests and runnable pre-edit applications with 2,331 hidden expert-authored acceptance criteria. Our judge-then-refute protocol grades criteria using source and browser evidence, challenges positive verdicts with a separate LLM verifier, and audits visual and interaction claims without gold code or target screenshots. Under a shared agentic harness, the strongest of ten model endpoints passes an average of 69.9% of criteria per task but fully satisfies only 26.4% of tasks. All ten endpoints achieve lower criterion completion on repository edits spanning three or four change types than on those spanning one or two. Co-Design Bench provides a testbed for studying the gap between partial requirement satisfaction and complete task success under agentic execution for real-user application revisions.

cs.AI

查看论文
arXiv ↗PDF ↗
首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1214ACL Anthology · ACL 2026

Beyond Scaling: Measuring and Predicting the Upper Bound of Knowledge Retention in Language Model Pre-Training

Changhao Jiang, Ming Zhang Fudan University, Yifei Cao Fudan University, Junjie Ye, Xiaoran Fan, Shihan Dou, Zhiheng Xi, Jiajun Sun Fudan University 等 15 位作者

原文摘要

The GPT-4 technical report suggests that downstream performance can be predicted from pre-training signals, but offers little methodological detail on how to quantify this. This work address this gap by modeling knowledge retention, the capacity of a pre-trained language model to memorize factual information from its corpus, and introduce a principled method to estimate it prior to training. We propose Size-dependent Mutual Information (SMI), an information-theoretic predictor that integrates knowledge frequency, knowledge specificity, and model size to forecast closed-book question answering (QA) accuracy. SMI is validated through large-scale document retrieval over the disclosed pre-training corpora of 21 public and 3 custom models, combined with a robust multi-template QA evaluation. Experiments show that SMI significantly outperforms repetition-based baselines and achieves R² > 0.7 in predicting QA accuracy for models above 1B parameters, without additional training. The analysis further reveals diminishing returns from scaling data and model size and provides evidence for an intrinsic upper bound on knowledge retention achievable by pre-training alone, motivating retrieval and other augmentation strategies.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1721ACL Anthology · ACL 2026

MiniRAG: A Lightweight RAG system with Small Language Models

Tianyu Fan, Jingyuan Wang, Xubin Ren, Chao Huang University of Hong Kong

原文摘要

The growing demand for efficient and lightweight Retrieval-Augmented Generation (RAG) systems has highlighted significant challenges when deploying Small Language Models (SLMs) in existing RAG frameworks. Current approaches face severe performance degradation due to SLMs’ limited semantic understanding and text processing capabilities, creating barriers for widespread adoption in resource-constrained scenarios. To address these fundamental limitations, we present MiniRAG, a novel RAG system designed for simplicity and efficiency. MiniRAG introduces two key technical innovations: (1) a semantic-aware heterogeneous graph indexing mechanism that combines text chunks and named entities in a unified structure, reducing reliance on complex semantic understanding, and (2) a lightweight topology-enhanced retrieval approach that leverages graph structures for efficient knowledge discovery without requiring advanced language capabilities. Our extensive experiments demonstrate that MiniRAG achieves comparable performance to LLM-based methods even when using SLMs while requiring only 25% of the storage space. Additionally, we contribute a comprehensive benchmark dataset for evaluating lightweight RAG systems under realistic on-device scenarios with complex queries.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.869ACL Anthology · ACL 2026

TLSA: LLM-Guided Text-Label Space Alignment with Contrastive Learning for Generalized Category Discovery

Wenxi Xu, Chuan Qin Chinese Academy of Sciences, Xi Chen, Chuyu Fang Baidu, Yuanchun Zhou Computer Network Information Center, Chinese Academy of Sciences,, Hengshu Zhu Computer Network Information Center, Chinese Academy of Sciences

原文摘要

Generalized Category Discovery (GCD) aims to classify data from partially labeled datasets by jointly recognizing known categories and discovering novel ones.Despite recent advances, existing methods still suffer from weak text–label alignment, inconsistent objectives across known and novel categories, and poor discrimination of semantically similar clusters. To mitigate these issues, we propose TLSA, a unified framework that enforces contrastive alignment between text and label representations within a shared semantic space. Specifically, we first design a label-semantic aware dual-encoder equipped with a symmetric contrastive objective to achieve text-label alignment. Then, we leverage LLM-based label induction to generate explicit and semantically meaningful names for previously unseen categories, followed by a graph-based refinement strategy that disambiguates semantically overlapping clusters through forced renaming. Finally, a confidence-aware sampling strategy ensures balanced learning across both easy and hard instances. Extensive experiments on four benchmark datasets show that TLSA consistently outperforms state-of-the-art GCD methods. The code is available at https://github.com/Wenxi-Xu/TLSA.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

版本更新 · v7arXiv:2505.12864Google Research

LEXam: Benchmarking Legal Reasoning on 340 Law Exams

Yu Fan, Jingwei Ni, Jakob Merane, Yang Tian, Yoan Hermstrüwer, Yinya Huang, Mubashara Akhtar, Etienne Salimbeni 等 17 位作者

原文摘要

Long-form legal reasoning remains a key challenge for large language models (LLMs) in spite of recent advances in test-time scaling. To address this, we introduce LEXam, a novel benchmark derived from 340 law exams spanning 116 law school courses across a range of subjects and degree levels. The dataset comprises 7,537 law exam questions in English and German. It includes both long-form, open-ended questions and multiple-choice questions with varying numbers of options. Besides reference answers, the open questions are also accompanied by explicit guidance outlining the expected legal reasoning approach such as issue spotting, rule recall, or rule application. Our evaluation on both open-ended and multiple-choice questions present significant challenges for current LLMs; in particular, they notably struggle with open questions that require structured, multi-step legal reasoning. Moreover, our results underscore the effectiveness of the dataset in differentiating between models with varying capabilities. Deploying an ensemble LLM-as-a-Judge paradigm with rigorous human expert validation, we demonstrate how model-generated reasoning steps can be evaluated consistently and accurately, closely aligning with human expert assessments. Our evaluation setup provides a scalable method to assess legal reasoning quality beyond simple accuracy metrics. Project page: https://lexam-benchmark.github.io/.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗