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

+1087新增论文
+804其中 AI 相关
+107已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-14 11:06 · 全站最近入库：2026-11-13 20:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-13 13:00 — 2026-11-14 13:00（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：2026-11-14 11:06最近发现新增版本：2026-11-13 20:44库内论文最新更新时间：2026-11-13 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。

23,348 已收录论文19,580 AI 相关6,727 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 19 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-14 11:04（北京时间）
新论文 · v1arXiv:2611.16590

AstroMemBench: A Benchmark for Memory Systems in Embodied Spacecraft Agents

You Wu, Guhong Zhang, Hongwei Li, Xinyue Hong, Yuan Jia

原文摘要

Long-term spacecraft autonomy requires embodied agents to use operational history under communication delays, time-critical operations, environmental uncertainty, complex physical interactions, power and computational constraints, and safety and reliability requirements. We introduce AstroMemBench and a Scenario-Challenge-Capability design method that maps these requirements to executable memory tests. The benchmark covers 16 memory subchallenges through 140 templates and 2240 instances across nine tasks in planetary surface operations, on-orbit servicing, and deep-space exploration. A deterministic environment scores actions for task completion, state changes, safety, and resource use. Ablations under nine conditions show that the benchmark is sensitive to how accurately agents recover and use historical information and to differences in memory-system design. Main experiments compare six configurations. Mem0, Chain-of-Memory, LightMem, and retrieval-augmented generation (RAG) improve same-session mean scores over native Pi Agent, with no clear advantage of the three memory systems over RAG. After a session restart, Mem0 outperforms RAG by 12.25 points. Benefits favor instruction retention and result reuse over ongoing state tracking and energy reservation. AstroMemBench supports the design, development, and selection of memory systems for embodied spacecraft agents. AstroMemBench 1.0 and its evaluation code are publicly available: https://github.com/flyingView/AstroMemBench-v1.

cs.AI · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12383

PCTac: Mechanochromic Photonic-Crystal Tactile Sensor for Dexterous Manipulation

Ruilin Zhang, Xuanshuo Liu, Junzhe Dai, Kefei Wu, Xuhao Qin, Ziyuan Jiao, Wanlin Li, Yurui Qu 等 9 位作者

原文摘要

Modern visuotactile sensors primarily sense contact by imaging the deformation of a compliant interface. Using techniques such as photometric stereo, they can recover detailed contact geometry, often represented as surface normals or depth. However, force-related information typically still needs to be inferred indirectly through calibration, geometric reconstruction, or learned mappings. Mechanochromic photonic-crystal (PC) materials offer an alternative physical encoding mechanism: contact loading changes their periodic microstructure and spectral response, directly transforming local stress into a spatially resolved structural-color field. Despite this potential, PC materials have rarely been explored as visuotactile sensors for closed-loop robot learning. We present PCTac, an open-source mechanochromic PC fingertip that uses a dense hue field as its tactile observation. Loading characterization demonstrates a repeatable relationship between the applied normal load and the observed hue response. We further integrate this representation directly into a Diffusion Policy and evaluate it on three real-robot manipulation tasks. Across 90 physical rollouts, PCTac Hue achieves 68 successes (75.6\%), compared with 60 (66.7\%) for PCTac RGB, 57 (63.3\%) for Wedge RGB, and 29 (32.2\%) for vision-only. PCTac Hue also achieves the highest observed success rate on each evaluated task, including Perturbed Test-Tube Insertion, where it achieves 16/30 successes versus 13/30 for tactile RGB baselines and 1/30 for vision-only. These results demonstrate the potential of mechanochromic structural color as a compact, load-sensitive tactile representation for robot learning and closed-loop manipulation. Project page: https://bey0ndt1me.github.io/PCTac-page/.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.41536

DAPS: Dependency-Aware Premise Selection for LLM Theorem Proving

Zixuan Chen, Wenyuan Jiang, Junling Wang, Mrinmaya Sachan, Yinya Huang

原文摘要

LLM-based theorem proving in Lean 4 has advanced rapidly, but provers are difficult to leverage newly contributed lemmas, because retrieval skews toward popular foundational lemmas, leaving the right premises buried among hundreds of thousands of candidates. Existing neural selectors rank candidates by semantic similarity, with three intrinsic limitations: frequency-skewed retrieval, isolated pairwise ranking, and degradation on out-of-distribution queries such as competition problems and informal language. Given that mathematics is structured by dependencies rather than similarities, we restore this signal to both the training data and the model. We curate two underused dependency resources. We conduct the first systematic mining of 53 Lean Blueprint projects, a previously untapped corpus of 3,805 manually curated informal+formal nodes that capture rare, research-level premises absent from Mathlib4. We further pair it with the extraction of comprehensive, typed, multi-level Mathlib4 dependencies. We then introduce DAPS, a dependency-aware premise selector with a structural neighborhood encoder, a group-level contrastive objective, and a Mathlib-then-Blueprint adaptation procedure. DAPS reaches 78.74 Recall@16 on Mathlib4-Heldout (+11.41 over the strong selector LeanHammer) and widens the margin to 7xrecall on competition-style queries. Downstream, its selected premises raise Goedel-Prover-V2-8B Pass@4 on miniF2F-test from 49.90 to 54.03 and improve all four general-purpose LLMs on the informal IMO-ProofBench (up to +11.4% relative). Project page: https://daps-eth.github.io/.

cs.LO · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.26239

CoRS: Fast Neural Flexible Job-Shop Scheduling via Composite Interval State Reuse

Sutong Jiang, Peng Zhao, Xuan Wu, Yan Wang, Jiaqi Wang, Rui Zhang, Yuan Jiang, You Zhou 等 9 位作者

原文摘要

Neural solvers for the Flexible Job-Shop Scheduling Problem (FJSP) typically refresh graph representations and update feasibility after every operation--machine decision. However, only feasibility must remain exact at every step, whereas graph encoding is substantially more expensive and can potentially be refreshed less frequently. We present CoRS, which decouples them: an interval-level graph representation is reused across multiple sequential decisions, while a stepwise feasibility state is updated after every action. This two-timescale design amortizes graph encoding without parallelizing action generation or relaxing scheduling constraints. CoRS further develops a feasibility-preserving composite-interval decoding scheme with dynamic constraint tracking and boundary state synchronization, which reduces representation refresh frequency while maintaining continuous feasible schedule construction. Furthermore, to alleviate representation staleness caused by interval-level state reuse, CoRS introduces enhanced static features as a compensation mechanism. By providing more comprehensive structural information of the scheduling problem, these features improve the model's perception of overall problem characteristics. Extensive experiments on synthetic and multiple public FJSP benchmarks demonstrate that CoRS significantly reduces inference time while maintaining competitive solution quality, achieving favorable speed-quality trade-offs under tight wall-clock budgets and low-latency scenarios.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.22154

混合贝叶斯-联结主义模型实现更准确的行为预测

More accurate behavioral predictions with hybrid Bayesian-connectionist models

Brenden M. Lake, Akshay K. Jagadish, Guangyuan Jiang

AI 速读 基于摘要

作者提出贝叶斯蒸馏与行为微调（BBT）方法，将贝叶斯模型的可解释先验与神经网络对复杂行为的拟合能力结合，并在人类概念学习的四个案例中报告了更优的行为预测表现。

cs.LG

arXiv ↗PDF ↗
查看原文摘要

Researchers must often choose between Bayesian or neural network models of behavior, two paradigms with complementary strengths and weaknesses. An ideal paradigm would facilitate testing many kinds of representations and inductive biases; Bayesian models make this easy, while neural networks do not. Similarly, an ideal paradigm would avoid over-simplifications; neural networks make this easy, while Bayesian models do not. Here, we introduce Bayesian distillation with Behavioral Tuning (BBT) as an approach to getting the best of both traditions. BBT offers a simple recipe for model building: first, a neural network is trained to mimic a Bayesian model through synthetic data, and second, the network is fine-tuned on human behavior to capture additional structure and nuance. Across four case studies in human concept learning, we find that BBT outperforms traditional approaches at predicting human behavior while also revealing psychological insights, resulting in models that can both mimic Bayesian priors and capture heuristics and biases that violate simple modeling assumptions.

新论文 · v1arXiv:2611.07634

AiXapply: Fast and Reliable Full-File Code Integration with Specialized Small Models for IDE Workflows

Siyuan Jiang, Xiang Cai, Peixu Wang, Yu Han, Yihong Dong, Wei Ning, Xuyuan Guo, Jincheng Wen 等 11 位作者

原文摘要

Large language models increasingly assist developers by proposing small code edits, yet reliably integrating a partial update snippet into an existing file while preserving unrelated content remains poorly supported by current code-generation workflows. We formalize the Code Integration (Apply) task as follows: given an original file and an update snippet, the system must produce the complete merged file while preserving all content outside the requested edit. We construct a high-quality multi-language dataset from real commits via a structured pipeline that converts code changes into update snippets paired with full-file ground truth and enforces consistency through verification and filtering. We then train a specialized 4B model, aiXapply, using supervised fine-tuning and reinforcement learning (GRPO). The supervised variant achieves 94.4% accuracy under our language-aware comparison, surpassing a strong large-model (Deepseek-V3.2) baseline (91.6%). Speculative decoding enables aiXapply-RL to reach $\sim$2700 tokens/s on a single A100 in a decoding subset; on the full benchmark, it achieves roughly 75$\times$ lower latency than the API-served Deepseek-V3.2 baseline. We further conduct an industrial deployment of aiXapply-RL in the aiXcoder IDE plugin as a dedicated Apply service, reducing mean Apply latency from 50 seconds to 1.89 seconds by offloading full-file generation from the upstream large model. Under time-based capacity planning, replacing one of five upstream serving instances would save 20% of upstream machine cost before the additional shared A100 service cost. Overall, our results demonstrate that treating code integration as a standalone task enables small models to achieve high accuracy, practical efficiency, and concrete industrial benefits in real-world IDE workflows where latency, cost and privacy are critical.

cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02845

Persuasion by Parts

Shuyuan Jia, Kangning Wang, Renzhe Xu

原文摘要

Classical Bayesian persuasion assumes that an information designer can condition signals on the entire state. We propose persuasion by parts. In this model, the receiver's payoff from acting is $X = \sum_{i=1}^n X_i$ for independent coordinates $X_1,\ldots,X_n$ observed by separate sources. The designer commits in advance to a product experiment, in which each source $i$ can condition its signal only on $X_i$. Given the signals, the receiver computes her posterior mean $y$ of $X$ and acts with probability $g(y)$, where $g\colon \mathbb{R} \to [0,1]$ is a nondecreasing function. The designer aims to maximize the probability of action. Let $V_{\mathrm{prod}}(g)$ and $V_{\mathrm{joint}}(g)$ be the supremum probabilities of action under persuasion by parts and under joint persuasion, respectively. When the designer knows $g$, we show $$ V_{\mathrm{prod}}(g) \;\ge\; c\,V_{\mathrm{joint}}(g)^2 \qquad\text{for every nondecreasing } g\colon \mathbb{R} \to [0,1], $$ where $c > 0$ is an absolute constant independent of $n$ and the prior; the exponent $2$ is tight. When $g$ is unknown, we construct a product experiment $Π$ from the prior alone, whose probability of action $V_Π(g)$ satisfies $$ V_Π(g) \;\ge\; c_\varepsilon\,V_{\mathrm{joint}}(g)^{2 + \varepsilon} \qquad\text{for every } \varepsilon > 0 \text{ and every nondecreasing } g\colon \mathbb{R} \to [0,1], $$ where $c_\varepsilon > 0$ depends only on $\varepsilon$.

cs.GT · econ.TH

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2607.06540

Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMs

Zhenyu Liu, Xuanyu Zhang, Yunxin Li, Qixun Teng, Shenyuan Jiang, Haolan Chen, Minjun Zhao, Fanbo Meng 等 13 位作者

原文摘要

Developing seamless, high-performance, native intelligent full-duplex Spoken Language Models (SLMs) remains a critical challenge and long-standing goal for the speech and NLP community. Despite notable progress, recent endeavors are fundamentally constrained by severe modality interference, which causes substantial knowledge degradation and compromises semantic integrity -- ultimately making full-duplex SLMs feel unnatural and unintelligent. In this paper, through an exhaustive fine-grained analysis of model optimization dynamics, we uncover the root cause of such performance degradation, revealing that modality interference arises from inherent gradient conflicts between acoustic and semantic modeling when the two modalities are forced to share a deep parameter space. Guided by this key insight, we introduce Lychee-FD, a native end-to-end full-duplex framework designed to mitigate modality interference. Importantly, we propose a hierarchical parameter separation strategy that decouples conflicting modalities in deep layers while preserving cross-modality coherence via a dedicated semantic alignment channel. Extensive experiments on multiple full-duplex benchmarks demonstrate that our method significantly advances the state of the art, yielding substantial improvements in both speech intelligence (+7.4% on Spoken QA) and full-duplex interaction fluidity (+28.5% on FullDuplexBench 1.5) without compromising inference efficiency. To the best of our knowledge, this work is the first to achieve two key advances: 1) uncovering and elucidating the root cause of modality interference in full-duplex SLMs, and 2) designing an elegant hierarchical model together with a practical solution for seamless, high-performance, native intelligent full-duplex SLMs.

cs.CL

查看论文
arXiv ↗PDF ↗
首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-demo.39ACL Anthology · ACL 2026

PaperMentor: A Human-Centered Multi-Agent Writing Tutor for AI Research Papers in Overleaf

Jiarui Liu, Terry Jingchen Zhang Vector Institute, Ryan Faulkner DeepMind, Xuanqiang Angelo Huang, Vilém Zouhar Department of Computer Science, ETHZ - ETH Zurich, Dominik Glandorf EPFL - EPF Lausanne, Isabel Dahlgren, Rishit Dagli University of Toronto 等 21 位作者

原文摘要

Expert writing feedback from experienced researchers is critical for early-career scholars to improve their manuscripts, yet high-quality feedback often remains scarce because reviewing research papers is labor-intensive. Emerging AI-powered writing assistants largely focus on grammar fixes or simulating peer review with final scores, yet they fall short of providing concrete, actionable suggestions that help students improve their papers during drafting. We present PaperMentor, a human-centered writing assistant system that delivers actionable suggestions as Overleaf-native inline comments while leaving the actual writing entirely to human authors. PaperMentor integrates an expert skill library carefully curated from established researchers’ writing advice with 12 specialized agents covering different aspects of paper writing, such as formatting compliance, phrasing accuracy, and terminology consistency. In a user study (n=14), 90.6% of the generated comments were rated actionable and 67.5% were rated valid, significantly outperforming a GPT-5.2 baseline without the skill library. We release PaperMentor as open source for public use.

cs.CL · cs.MA

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-industry.33ACL Anthology · ACL 2026

Learning from Textual Radiology Reports: A Benchmark Dataset for Coronary CT Angiography

Sudharshan Balaji, Zhiyu Liu, Zhengyuan Jiang, Shuo Lei, Yimin Chen, Yang Xiao, Shone O. Almeida, Mathew Joseph Karivelil 等 10 位作者

原文摘要

While coronary imaging is widely used for anatomical assessment, CCTA reports play a distinct last-mile role in clinical care. Ratherthan serving as an intermediate signal, CCTA provides an assessment of coronary disease severity (known as the CAD-RADS score) toguide patient management. However, real-world clinical text exhibits substantial heterogeneity in terminology and structure, leadingto inconsistent interpretation by automated systems, even for clinically similar cases. Recent work leverages a direct application ofLLMs for automated CAD-RADS scoring, but is limited by small, non-public, and homogeneous clinical data. We introduce CCTA-RADS, the largest publicly available dataset of 940 real-world CCTA reports from a major cardiovascular center, each annotated with CAD-RADS scores. Our analysis reveals that direct approaches, including state-of-the-art LLMs (GPT-4o, GPT-o3) and fine-tuned BERT models underperform on diverse real-world clinical data. To address these limitations, we propose a two-stage pipeline that decouples structuring from classification: an LLM-based parser normalizes heterogeneous reports into structured format, followed by fine-tuned BERT classification. This approach substantially improves the F1-score by 6%-13% compared with direct methods. We deploy our system as an interactive web interface that allows clinicians to upload CCTA reports for automated CAD-RADS assessment with SHAP and LIME explainability visualizations.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1263ACL Anthology · ACL 2026

Beyond Single View: A Comprehensive Benchmark for Medical Multimodal Large Language Models on Multi-Image Understanding

Dexuan Xu, Yuan Jiayin, Jianing Wang Peking University, Yanyuan Chen, Hanpin Wang Peking University, Yu Huang Peking University

原文摘要

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in interpreting single medical images. However, real-world clinical diagnosis is intrinsically a multi-view process, requiring the synthesis of information across volumetric slices, temporal sequences, and comparative modalities. Existing benchmarks fail to capture this complexity, limiting the assessment of models in realistic clinical workflows. To bridge this gap, we introduce MedMultiBench, the first large-scale benchmark specifically designed for medical multi-image understanding. Comprising 11,392 expert-curated samples, MedMultiBench evaluates MLLMs across four distinct dimensions: Joint Reasoning, Comparative Analysis, Comprehensive Perception, and In-Context Learning. We benchmark 13 state-of-the-art MLLMs, revealing that while current models excel in single-view tasks, they struggle significantly with multi-image contexts. Our experiments identify a performance degradation in open-source models when processing increased visual loads, whereas closed-source models demonstrate better scalability. MedMultiBench provides a robust framework to facilitate the development of MLLMs capable of holistic clinical reasoning.

cs.CL · cs.CV

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.1273ACL Anthology · ACL 2026

Achieving Multi-Hop Calculation and Safe Abstention in Financial Numerical Reasoning by Metric Graph Constrained LLMs

Aoyuan Jiang Wuhan University, Liang Hong Wuhan University, Haoxuan Liu, Rui Wang

原文摘要

Financial numerical reasoning demands rigorous adherence to domain-specific logic and precise evidence foundation. However, large language models (LLMs) are prone to forced generation when confronting ambiguous evidence or complex recursive dependencies, often hallucinating values to bridge information gaps. To address this, we propose graph-bounded financial reasoning (GBFR), a neuro-symbolic framework that imposes semantic and structural constraints via a financial metric knowledge graph (FMKG). Unlike sequential generation paradigms, our approach employs a parallel graph-constrained reasoning algorithm that orchestrates specialized operators to simultaneously explore heterogeneous derivation paths of complex financial metrics. Through cross-path verification, the framework aggregates only semantically consistent results, ensuring reasoning is bounded by available context. Crucially, this approach enables safe abstention by distinguishing genuine data absence from retrieval failure, thereby preventing ungrounded fabrication. To evaluate this capability, we further construct counterfactual samples by perturbing entities, times, and metrics to synthesize unanswerable scenarios. Empirical evaluations on standard benchmarks demonstrate that GBFR significantly outperforms state-of-the-art baselines.

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.1354ACL Anthology · ACL 2026

SILO-BENCH: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systems

Yuzhe Zhang Beijing University of Technology, Feiran Liu College of Computer Science, Yi Shan Beijing University of Technology, Xinyi Huang, Xin Yang Kuaishou- 快手科技 and Zhejiang University, Yueqi Zhu, Xuxin Cheng, Cao Liu 等 11 位作者

原文摘要

Large language models are increasingly deployed in multi-agent systems to overcome context limitations by distributing information across agents. However, whether LLM-based agents can reliably coordinate when each observes only a fragment of the global problem remains unclear. Existing benchmarks often prescribe agent roles or interaction patterns, conflating coordination ability with role-based priors. We introduce SILO-BENCH, a role-free benchmark for evaluating free-form collaboration under information silos. The benchmark comprises 30 algorithmic tasks with exact ground-truth answers, organized into 3 complexity levels based on optimal communication complexity: aggregation, mesh, and global shuffle. To systematically probe coordination capabilities, we instantiate 54 configurations by varying 3 communication protocols, 6 agent scales and 3 frontier LLMs, conducting 1,620 experiments. We evaluate agent behavior along three dimensions: Success Rate, Token Consumption, and Communication Density. Our experiments reveal a fundamental Communication-Reasoning Gap: agents communicate actively, yet fail to translate interaction into effective distributed computation. Performance collapses as complexity increases, with Level-III tasks achieving zero success beyond 50 agents. These findings demonstrate that current LLMs cannot escape information silos through coordination alone. SILO-BENCH provides a foundation for tracking progress toward genuinely collaborative multi-agent systems. The code is available at https://github.com/jwyjohn/acl26-silo-bench.

cs.CL · cs.MA

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.1533ACL Anthology · ACL 2026

PIArena: A Platform for Prompt Injection Evaluation

Runpeng Geng, Chenlong Yin Pennsylvania State University, Yanting Wang, Ying Chen Pennsylvania State University, Pennsylvania State University, Jinyuan Jia Pennsylvania State University

原文摘要

Prompt injection attacks pose serious security risks across a wide range of real-world applications. While receiving increasing attention, the community faces a critical gap: the lack of a unified platform for prompt injection evaluation. This makes it challenging to reliably compare defenses, understand their true robustness under diverse attacks, or assess how well they generalize across tasks and benchmarks. For instance, many defenses initially reported as effective were later found to exhibit limited robustness on diverse datasets and attacks. To bridge this gap, we introduce PIArena, a unified and extensible platform for prompt injection evaluation that enables users to easily integrate state-of-the-art attacks and defenses and evaluate them across a variety of existing and new benchmarks. We also design a dynamic strategy-based attack that adaptively optimizes injected prompts based on defense feedback. Through comprehensive evaluation using PIArena, we uncover critical limitations of state-of-the-art defenses: limited generalizability across tasks, vulnerability to adaptive attacks, and fundamental challenges when an injected task aligns with the target task. The code and datasets are available at https://github.com/sleeepeer/PIArena.

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.1693ACL Anthology · ACL 2026

Test of Time: Rethinking Temporal Signal of Benchmark Contamination

Terry Jingchen Zhang Vector Institute, Gopal Dev EuroSafeAI, Max-Planck Institute and Jinesis Lab, University of Toronto & Vector Institute, Ning Wang ETHZ - ETH Zurich, Max Obreiter ETHZ - ETH Zurich, Punya Syon Pandey University of Toronto, Keenan Samway Max Planck Institute for Intelligent Systems, Max-Planck Institute, Wenyuan Jiang ETHZ - ETH Zurich, Yinya Huang ETH Zurich 等 11 位作者

原文摘要

Post-cutoff performance decay of LLMs has been widely interpreted as a temporal signal for benchmark contamination, where public information released before the training cutoff may have been included into training corpora and inflated model performance by memorization. We critically examine this view and demonstrate that this temporal signal is highly sensitive to how benchmark questions are constructed, even if the underlying source material remains invariant. Specifically, we show that LLM-transformed questions can produce remarkably different temporal patterns compared to fill-in-the-blank (cloze) questions directly retrieved from the very same documents. We validate this effect on prior benchmarks that report clear post-cutoff decay (LiveCodeBench), and show that a simple LLM-driven transformation of the same problems can effectively remove the temporal pattern. We further provide a mechanistic understanding of this phenomenon using influence function analysis. Overall, our results suggest that post-cutoff performance decay is a sensitive contamination signal, motivating more robust contamination probes for reliable LLM evaluation.

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.1781ACL Anthology · ACL 2026

CAMEC: Complexity-Aware Multi-Expert Collaboration for Reliable Chinese Medical Question Answering

Yukang Wu, Xiyuan Jia, Jiayi Wu, HongChen Yu, Yuhan Qiu, Wu Guohua Hangzhou Dianzi University

原文摘要

Large language models (LLMs) are promising for medical question answering (QA) but remain unreliable in Chinese clinical settings due to hallucinations, weak factual grounding, and difficulty handling clinically complex cases. We propose CAMEC (Complexity-Aware Multi-Expert Collaboration), a framework that combines hierarchical medical adaptation with complexity-aware expert routing for reliable Chinese medical QA. We adopt a three-stage LoRA-based supervised fine-tuning pipeline for domain adaptation, instruction following, and clinical reasoning. At inference, CAMEC routes each query by predicted complexity and selectively recruits three experts: an internal chain-of-thought (CoT) expert, a retrieval-augmented expert over a dense medical vector database, and a knowledge graph (KG) expert over a structured medical knowledge base. An LLM-as-a-Judge module evaluates and critiques expert reports, iteratively refining them into a consensus answer. Experiments on four Chinese medical benchmarks show that CAMEC consistentlyoutperforms strong general and medical LLM baselines, achieving 78.86% (CMExam), 84.15% (MedQA-CN), 78.51% (CMMLU-Med), and 74.40% (CMB-exam), with consistent absolute improvements over the previous state-of-the-artHuatuoGPT-o1-7B across all benchmarks. The complexity-aware router reduces expert invocations and inference cost, making CAMEC both highly effective and computationally efficient.

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.412ACL Anthology · ACL 2026

UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity Mixture-of-Experts

Zhenyu Liu, Yunxin Li Harbin Institute of Technology, Xuanyu Zhang, Qixun Teng, Shenyuan Jiang Dayu Algorithms Team, Xinyu Chen, Haoyuan Shi, Haolan Chen Tencent 等 15 位作者

原文摘要

Recent advances in unified multimodal models indicate a clear trend towards comprehensive content generation. However, the auditory domain remains a significant challenge, with music and speech often developed in isolation, hindering progress towards universal audio synthesis. This separation stems from inherent task conflicts between semantic speech and structural music modeling, and severe data imbalances, which impede the development of a truly unified model. To address these challenges, we propose UniMoE-Audio a unified speech and music generation model built upon a novel Dynamic-Capacity Mix-of-Experts (DCMoE) framework. Architecturally, UniMoE-Audio extends the conventional MoE paradigm by introducing a Top-P routing strategy for adaptive capacity allocation. To tackle data imbalance, we introduce a three-stage training curriculum: 1) Independent Specialist Training leverages original datasets to instill domain-specific knowledge into each specialists without interference; 2) MoE Integration and Warmup incorporates these specialists into the UniMoE-Audio architecture, warming up the gate module and shared expert using a subset of balanced dataset; and 3) Synergistic Joint Training trains the entire model end-to-end on the fully balanced dataset, fostering enhanced cross-domain synergy. Extensive experiments show that UniMoE-Audio not only achieves state-of-the-art performance on major speech and music generation benchmarks, but also demonstrates superior synergistic learning, mitigating the performance degradation typically seen in naive joint training. Our findings highlight the substantial potential of specialized MoE architecture and curated training strategies in advancing universal audio generation.

cs.CL · cs.CV

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.419ACL Anthology · ACL 2026

Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMs

Zhenyu Liu, Xuanyu Zhang, Yunxin Li Harbin Institute of Technology, Qixun Teng, Shenyuan Jiang Dayu Algorithms Team, Haolan Chen Tencent, Mingjun Zhao, Fanbo Meng 等 13 位作者

原文摘要

Developing seamless, high-performance, native intelligent full-duplex Spoken Language Models (SLMs) remains a critical challenge and long-standing goal for the speech and NLP community. Despite notable progress, recent endeavors are fundamentally constrained by severe modality interference, which causes substantial knowledge degradation and compromises semantic integrity─ultimately making full-duplex SLMs feel unnatural and unintelligent. In this paper, through an exhaustive fine-grained analysis of model optimization dynamics, we uncover the root cause of such performance degradation, revealing that modality interference arises from inherent gradient conflicts between acoustic and semantic modeling when the two modalities are forced to share a deep parameter space. Guided by this key insight, we introduce Lychee-FD, a native end-to-end full-duplex framework designed to mitigate modality interference. Importantly, we propose a hierarchical parameter separation strategy that decouples conflicting modalities in deep layers while preserving cross-modality coherence via a dedicated semantic alignment channel. Extensive experiments on multiple full-duplex benchmarks demonstrate that our method significantly advances the state of the art, yielding substantial improvements in both speech intelligence (+7.4% on Spoken QA) and full-duplex interaction fluidity (+28.5% on FullDuplexBench 1.5) without compromising inference efficiency. To the best of our knowledge, this work is the first to achieve two key advances: 1) uncovering and elucidating the root cause of modality interference in full-duplex SLMs, and 2) designing an elegant hierarchical model together with a practical solution for seamless, high-performance, native intelligent full-duplex SLMs.

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.541ACL Anthology · ACL 2026

Fingerprinting LLMs via Prompt Injection

Yuepeng Hu, Zhengyuan Jiang Duke University, Mengyuan Li, Osama Ahmed Facebook, Zhicong Huang Ant Group, Cheng Hong Ant Group, Neil Zhenqiang Gong

原文摘要

Large language models (LLMs) are often modified after release through post-processing such as post-training or quantization, which makes it challenging to determine whether one model is derived from another. Existing provenance detection methods have two main limitations: (1) they embed signals into the base model before release, which is infeasible for already published models, or (2) they compare outputs across models using hand-crafted or random prompts, which are not robust to post-processing. In this work, we propose LLMPrint, a novel detection framework that constructs fingerprints by exploiting LLMs’ inherent vulnerability to prompt injection. Our key insight is that by optimizing fingerprint prompts to enforce consistent token preferences, we can obtain fingerprints that are both unique to the base model and robust to post-processing. We further develop a unified verification procedure that applies to both gray-box and black-box settings, with statistical guarantees. We evaluate LLMPrint on five base models and around 700 post-trained or quantized variants. Our results show that LLMPrint achieves high true positive rates while keeping false positive rates near zero. The code is publicly available at https://github.com/hifi-hyp/ACL-LLMPrint.

cs.CL

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