跳转至

ACL 2026 · 全部收录(459 篇)

仅列出通过预过滤且已打分的论文;分数是「评测方法学价值」,不是会议录用质量。 返回总览

# 论文 轨道 分数 链接
301 Are they lovers or friends? Evaluating LLMs’ Social Reasoning in English and Korean Dialogues Long 6 页 · PDF
302 ArgGenBench: Benchmarking the Complex Controlled Argument Generation Capability of Large Language Models Long 6 页 · PDF
303 Author-in-the-Loop Response Generation and Evaluation: Integrating Author Expertise and Intent in Responses to Peer Review Long 6 页 · PDF
304 Automatic and Reliable Evaluation for Academic Caption-to-Figure Generation with LMMs Long 6 页 · PDF
305 BaseCal: Unsupervised Confidence Calibration via Base Model Signals Long 6 页 · PDF
306 Benchmarking and Learning Real-World Customer Service Dialogue Long 6 页 · PDF
307 Beyond Scaling: Measuring and Predicting the Upper Bound of Knowledge Retention in Language Model Pre-Training Long 6 页 · PDF
308 BoYaEval: Evaluating Multimodal Large Language Models on Understanding Ancient Chinese Musical Scores Long 6 页 · PDF
309 Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders Long 6 页 · PDF
310 Business as Rulesual: A Benchmark and Framework for Business Rule Flow Modeling with LLMs Long 6 页 · PDF
311 CEDAR: A Chinese Evaluation Dataset for Computational Argumentation Long 6 页 · PDF
312 Characterizing and Evaluating Working Emotion Vocabularies in Multilingual Large Language Models Long 6 页 · PDF
313 ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch Long 6 页 · PDF
314 CityCube: Benchmarking Cross-view Spatial Reasoning on Vision-Language Models in Urban Environments Long 6 页 · PDF
315 CloneMem: Benchmarking Long-Term Memory for AI Clones Long 6 页 · PDF
316 CNSL-bench: Benchmarking the Sign Language Understanding Capabilities of MLLMs on Chinese National Sign Language Long 6 页 · PDF
317 CogEvolve: A Multimodal Benchmark for Evaluating Relational Reasoning in Semantic Extension Long 6 页 · PDF
318 Confident, Calibrated, or Complicit: Safety Alignment and Ideological Bias in LLM Hate Speech Detection Long 6 页 · PDF
319 Deep Research with Open-Domain Evaluation and Multi-Stage Guardrails for Safety Long 6 页 · PDF
320 Demystifying Uncertainty in LLMs: Active Calibration between Concepts and Human Evaluations Long 6 页 · PDF
321 DiningBench: A Hierarchical Multi-view Benchmark for Perception and Reasoning in the Dietary Domain Long 6 页 · PDF
322 EduBench: A Comprehensive Benchmarking Dataset for Evaluating Large Language Models in Diverse Educational Scenarios Long 6 页 · PDF
323 EGSS: Entropy-guided Stepwise Scaling for Reliable Software Engineering Long 6 页 · PDF
324 Evaluating Structure-Aware Retrieval and Safety in Statute-Centric Legal QA Long 6 页 · PDF
325 Evaluating the Expressive Appropriateness of Speech in Rich Contexts Long 6 页 · PDF
326 FAIRGAMER: Evaluating Social Biases in LLM-Based Video Game NPCs Long 6 页 · PDF
327 False Friends or Cognates? A Cross-lingual Semantic Ambiguity Evaluation for Galician, Portuguese and Spanish Long 6 页 · PDF
328 FinChart-Bench: Benchmarking Financial Chart Comprehension in Vision-Language Models Long 6 页 · PDF
329 From Recognition to Reasoning: Benchmarking and Enhancing MLLMs on Real-World Receipt Document Understanding Long 6 页 · PDF
330 Full-Duplex-Bench-v2: A Multi-Turn Evaluation Framework for Duplex Dialogue Systems with an Automated Examiner Short 6 页 · PDF
331 GenomeQA: Benchmarking General Large Language Models for Genome Sequence Understanding Long 6 页 · PDF
332 GeoLaux: A Benchmark for Evaluating MLLMs’ Geometry Performance on Long-Step Problems Requiring Auxiliary Lines Long 6 页 · PDF
333 GQLBench: A Large-Scale Cross-Domain, Cross-Dialect Benchmark for NL2GQL Long 6 页 · PDF
334 HarDBench: A Benchmark for Draft-Based Co-Authoring Jailbreak Attacks for Safe Human–LLM Collaborative Writing Long 6 页 · PDF
335 How Good is Your Wikipedia? Auditing Data Quality for Low-resource and Multilingual NLP Long 6 页 · PDF
336 HumanLLM: Benchmarking and Improving LLM Anthropomorphism via Human Cognitive Patterns Long 6 页 · PDF
337 IGenBench: Benchmarking the Reliability of Text-to-Infographic Generation Long 6 页 · PDF
338 InsideOut: Measuring and Mitigating Insider–Outsider Bias in Interview Script Generation Long 6 页 · PDF
339 Iterative Dual-Model Alignment for Story Evaluation Long 6 页 · PDF
340 J4R: Learning to Judge with Equivalent Initial State Group Relative Policy Optimization Long 6 页 · PDF
341 KoCo-Bench: Can Large Language Models Leverage Domain Knowledge in Software Development? Long 6 页 · PDF
342 LaoBench: A Large-Scale Multidimensional Lao Benchmark for Large Language Models Long 6 页 · PDF
343 Learning from Emptiness: De-biasing Listwise Rerankers with Content-Agnostic Probability Calibration Short 6 页 · PDF
344 LogicEval: A Systematic Framework for Evaluating Automated Repair Techniques for Logical Vulnerabilities in Real-World Software Long 6 页 · PDF
345 M3-VQA: A Benchmark for Multimodal, Multi-Entity, Multi-Hop Visual Question Answering Long 6 页 · PDF
346 Measuring User’s Mental Models of Speech Translation in Human-AI Collaboration Long 6 页 · PDF
347 MetaBench: A Multi-task Benchmark for Assessing LLMs in Metabolomics Long 6 页 · PDF
348 MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Long-tail Knowledge Long 6 页 · PDF
349 MirrorQA: Benchmarking Multimodal LLMs on Mirror-Orientation Reasoning Long 6 页 · PDF
350 ModeX: Evaluator-Free Best-of-N Selection for Open-Ended Generation Long 6 页 · PDF
351 MSEarth: A Multimodal Benchmark for Earth Science Phenomenon Discovery with MLLMs Long 6 页 · PDF
352 Musical Score Understanding Benchmark: Evaluating Large Language Models’ Comprehension of Complete Musical Scores Long 6 页 · PDF
353 N-GLARE: An Non-Generative Latent Representation-Efficient LLM Safety Evaluator Long 6 页 · PDF
354 Omni-I2C: A Holistic Benchmark for High-Fidelity Image-to-Code Generation Long 6 页 · PDF
355 OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Online Shopping Behavior Simulation Long 6 页 · PDF
356 OSCBench: Benchmarking Object State Change in Text-to-Video Generation Long 6 页 · PDF
357 POLYCHARTQA: Benchmarking Large Vision-Language Models with Multilingual Chart Question Answering Long 6 页 · PDF
358 PRiSM: Benchmarking Phone Realization in Speech Models Long 6 页 · PDF
359 ProactiveEval: A Unified Evaluation Framework for Proactive Dialogue Agents Long 6 页 · PDF
360 Pub-LawBench: Public-Oriented Benchmarking for LegalAI Long 6 页 · PDF
361 RealChart2Code: Bridging the Gap in Real-World Chart-to-Code Generation via Multi-Task Evaluation Long 6 页 · PDF
362 RealTalk-CN: A Realistic Chinese Speech Task-Oriented Dialogue Benchmark with Cross-Modal Analysis Long 6 页 · PDF
363 ReCoQA: A Benchmark for Tool-Augmented and Multi-Step Reasoning in Real Estate Question and Answering Long 6 页 · PDF
364 ReFEree: Reference-Free and Fine-Grained Method for Evaluating Factual Consistency in Real-World Code Summarization Long 6 页 · PDF
365 Rethinking Meeting Effectiveness: A Benchmark and Framework for Temporal Fine-grained Automatic Meeting Effectiveness Evaluation Long 6 页 · PDF
366 REVEALER: Reinforcement-Guided Visual Reasoning for Element-Level Text-Image Alignment Evaluation Long 6 页 · PDF
367 Revisiting a Pain in the Neck: A Semantic Reasoning Benchmark for Language Models Long 6 页 · PDF
368 Reward Modeling for Scientific Writing Evaluation Long 6 页 · PDF
369 SAHM: A Benchmark for Arabic Financial and Shari’ah-Compliant Reasoning Long 6 页 · PDF
370 SDiaReward: Modeling and Benchmarking Spoken Dialogue Rewards with Modality and Colloquialness Long 6 页 · PDF
371 ShopSimulator: Evaluating and Exploring RL-Driven LLM Agent for Shopping Assistants Long 6 页 · PDF
372 SkMTEB: Slovak Massive Text Embedding Benchmark and Model Adaptation Long 6 页 · PDF
373 SubTokenTest: A Practical Benchmark for Real-World Sub-token Understanding Long 6 页 · PDF
374 TaxPraBen: A Scalable Benchmark for Structured Evaluation of LLMs in Chinese Real-World Tax Practice Long 6 页 · PDF
375 Tears or Cheers? Benchmarking LLMs via Culturally Elicited Distinct Affective Responses Long 6 页 · PDF
376 The Retrieval Bottleneck: Scaling Laws for Reinforcement Learning in RAG Long 6 页 · PDF
377 To Judge or Not to Judge: Can Large Language Models Leverage the Dispute Focus in Legal Judgment? Long 6 页 · PDF
378 TrendFact: A Benchmark Towards Hotspot Perception in Automatic Fact-Checking Long 6 页 · PDF
379 UniDataBench: Evaluating Data Analytics Agents Across Structured and Unstructured Data Long 6 页 · PDF
380 UNIKIE-BENCH: Benchmarking Large Multimodal Models for Key Information Extraction in Visual Documents Long 6 页 · PDF
381 v-HUB: A Benchmark for Video Humor Understanding from Vision and Sound Long 6 页 · PDF
382 VideoCuRL: Video Curriculum Reinforcement Learning with Orthogonal Difficulty Decomposition Long 6 页 · PDF
383 What About the Scene With the Hitler Reference? HAUNT: A Framework to Probe LLMs’ Self-consistency in Closed Domains Via Adversarial Nudge Long 6 页 · PDF
384 When Efficiency Meets Safety: A Benchmark Security Analysis of KV Cache Compression in Large Language Models Long 6 页 · PDF
385 Who Wrote This Line? Evaluating the Detection of LLM-Generated Classical Chinese Poetry Long 6 页 · PDF
386 Act-Adaptive Margin: Dynamically Calibrating Reward Models for Subjective Ambiguity Long 5 页 · PDF
387 Benchmarking and Enabling Efficient Chinese Medical Retrieval via Asymmetric Encoders Long 5 页 · PDF
388 Benchmarking Large Vision-Language Models on CFMME: A Comprehensive Chinese Financial Multimodal Evaluation Dataset Long 5 页 · PDF
389 Beyond Majority Voting: Towards Fine-grained and More Reliable Reward Signal for Test-Time Reinforcement Learning Long 5 页 · PDF
390 CASS: Nvidia to AMD Transpilation with Data, Models, and Benchmark Long 5 页 · PDF
391 CITE: Benchmarking Heterogeneous Text-Attributed Graph Models Long 5 页 · PDF
392 CL2GEC: A Multi-Discipline Benchmark for Continual Learning in Chinese Literature Grammatical Error Correction Long 5 页 · PDF
393 Community-Aware Assessment of Social Textual Engagement and Resonance: A Human-Centric Perspective on User-Generated Content Evaluation Long 5 页 · PDF
394 Cross-Modal Coreference Alignment: Enabling Reliable Information Transfer in Omni-LLMs Long 5 页 · PDF
395 DefGen-Bench: A Benchmark for Chinese Criminal Defence Opinion Generation in LegalAI Long 5 页 · PDF
396 Deliberative Searcher: Improving LLM Reliability via Reinforcement Learning with Constraints Long 5 页 · PDF
397 Difficulty-Controllable Cloze Question Distractor Generation Long 5 页 · PDF
398 DUD: Decoupled Update Dynamics for Reliable Uncertainty Quantification in Large Language Models Long 5 页 · PDF
399 Efficient Self-Evaluation for Diffusion Language Models via Sequence Regeneration Long 5 页 · PDF
400 Evaluating LLMs on Large-Scale Graph Property Estimation via Random Walks Long 5 页 · PDF
401 FedMental: Evaluating Federated Learning for Mental Health Detection from Social Media Data Long 5 页 · PDF
402 FinCall-Surprise: A Large Scale Multi-modal Benchmark for Earning Surprise Prediction Long 5 页 · PDF
403 Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs Long 5 页 · PDF
404 Gained in Translation: Privileged Pairwise Judges Enhance Multilingual Reasoning Long 5 页 · PDF
405 GraphSynth: Resolving the Diversity-Reliability Trade-off with Probabilistic Factor Graphs Long 5 页 · PDF
406 Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding Long 5 页 · PDF
407 Mitigating Context Interference for Reliable and Efficient Search Agents Long 5 页 · PDF
408 Multimodal Safety Evaluation in Generative Agent Social Simulations Long 5 页 · PDF
409 Perplexity-Aware Data Scaling Law: Perplexity Landscapes Predict Performance for Continual Pre-training Long 5 页 · PDF
410 PodBench: A Comprehensive Benchmark for Instruction-Aware Audio-Oriented Podcast Script Generation Long 5 页 · PDF
411 Reasoning with OmniThought: A Large CoT Dataset with Verbosity and Cognitive Difficulty Annotations Long 5 页 · PDF
412 Reliable Use of Lemmas via Eligibility Reasoning and Section-Aware Reinforcement Learning Short 5 页 · PDF
413 RSMeM: Knowledge-Enhanced Memory Evolution for Remote Sensing Agents with Systematic Evaluation Long 5 页 · PDF
414 Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning Long 5 页 · PDF
415 Sign-Language Datasets at Scale: A Comprehensive Survey on Resources, Benchmarks, and Annotation Standards Long 5 页 · PDF
416 Tailoring Diagnostic Modeling to Individual Learners: Personalized Distractor Generation via MCTS-Guided Reasoning Reconstruction Long 5 页 · PDF
417 Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Short 5 页 · PDF
418 TRAC: Teacher-Guided Token Reward with Adaptive Calibration for Robust Policy Optimization Long 5 页 · PDF
419 VIB-Probe: Detecting and Mitigating Hallucinations in Vision-Language Models via Variational Information Bottleneck Long 5 页 · PDF
420 Achieving Multi-Hop Calculation and Safe Abstention in Financial Numerical Reasoning by Metric Graph Constrained LLMs Long 4 页 · PDF
421 All Changes May Have Invariant Principles: Improving Ever-Shifting Harmful Meme Detection via Design Concept Reproduction Long 4 页 · PDF
422 AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage Long 4 页 · PDF
423 Benchmarking Post-Training Quantization of Large Language Models under Microscaling Floating Point Formats Long 4 页 · PDF
424 Calibration-Aware Policy Optimization for Reasoning LLMs Long 4 页 · PDF
425 CAMEC: Complexity-Aware Multi-Expert Collaboration for Reliable Chinese Medical Question Answering Long 4 页 · PDF
426 Causal-ESC: Reliable Policy Learning for Emotional Support Conversation via Causal Inference Long 4 页 · PDF
427 Comparative Analysis of the Intrinsic Metrics for Tokenizers and their effect on Downstream Tasks for Hindi and Marathi Long 4 页 · PDF
428 Distillation Traps and Guards: A Calibration Knob for LLM Distillability Long 4 页 · PDF
429 ET-Agent: Incentivizing Effective Tool-Integrated Reasoning Agent via Behavior Calibration Long 4 页 · PDF
430 Evaluating the Impact of Verbal Multiword Expressions on Machine Translation Long 4 页 · PDF
431 Exploring Layer Activation Dynamic of CoT via Knowledge Probe Long 4 页 · PDF
432 LegalGraphRAG: Multi-Agent Graph Retrieval-Augmented Generation for Reliable Legal Reasoning Long 4 页 · PDF
433 LLM4Cell: Taxonomy and Evaluation of LLM and Agentic Models for Single-Cell Biology Long 4 页 · PDF
434 Luring as a Proxy: Evaluating Corpus Transferability for Cybergrooming Detection Short 4 页 · PDF
435 Personalizing LLMs with Binary Feedback: A Preference-Calibrated Optimization Framework Long 4 页 · PDF
436 Scaling Law for Multimodal Large Language Model Supervised Fine-Tuning Long 4 页 · PDF
437 Scaling Laws for Code: A More Data-Hungry Regime Long 4 页 · PDF
438 Think How to Think: Mitigating Overthinking with Autonomous Difficulty Cognition in Large Reasoning Models Long 4 页 · PDF
439 Translation with Thought: Difficulty-Adaptive Reasoning via Reinforcement Learning for Multi-Domain Machine Translation Long 4 页 · PDF
440 Why Are We Moral? An LLM-based Agent Simulation Approach to the Study of Moral Evolution Long 4 页 · PDF
441 A BERTology View of LLM Orchestrations: Token- and Layer-Selective Probes for Efficient Single-Pass Classification Long 3 页 · PDF
442 Calibrating Inference Time Alignment with Sequence-level Risk Accumulation Long 3 页 · PDF
443 From Answers to Arguments: Toward Trustworthy Clinical Diagnostic Reasoning with Toulmin-Guided Curriculum Goal-Conditioned Learning Long 3 页 · PDF
444 Generating then Refining for Reliable Knowledge Base Question Answering Long 3 页 · PDF
445 MedVerse: Efficient and Reliable Medical Reasoning via DAG-Structured Parallel Execution Long 3 页 · PDF
446 ParaCodex: A Profiling-Guided Autonomous Coding Agent for Reliable Parallel Code Generation and Translation Long 3 页 · PDF
447 Psyche-R1: Towards Reliable Psychological LLMs through Unified Empathy, Expertise, and Reasoning Long 3 页 · PDF
448 SDE-SQL: Enhancing Text-to-SQL Generation in Large Language Models via Self-Driven Exploration with SQL Probes Long 3 页 · PDF
449 Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluation Long 3 页 · PDF
450 Where Paths Split: Localized, Calibrated Control of Moral Reasoning in Large Language Models Long 3 页 · PDF

评论