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
151 AutoTaskEval: Towards Domain-Specific and Fine-Grained Evaluation for LLMs Long 7 页 · PDF
152 Benchmarking Egocentric Clinical Intent Understanding Capability for Medical Multimodal Large Language Models Long 7 页 · PDF
153 Benchmarking LLM’s Capability in Reasoning over Conflicting Web References Long 7 页 · PDF
154 Beyond Detection: Evaluating Fallacy Awareness of LLMs in Interactive Scenarios Long 7 页 · PDF
155 Beyond Itinerary Planning—A Real-World Benchmark for Multi-Turn and Tool-Using Travel Tasks Long 7 页 · PDF
156 Beyond Literal Mapping: Benchmarking and Improving Non-Literal Translation Evaluation Long 7 页 · PDF
157 Beyond Single View: A Comprehensive Benchmark for Medical Multimodal Large Language Models on Multi-Image Understanding Long 7 页 · PDF
158 Beyond Word Boundaries: A Hebrew Coreference Benchmark and an Evaluation Protocol for Morphologically Complex Text Long 7 页 · PDF
159 Bidirectional LMs are Better Knowledge Memorizers? A Benchmark for Real-world Knowledge Injection Long 7 页 · PDF
160 Calibrated? Not for Everyone: How Sexual Orientation and Religious Markers Distort LLM Accuracy and Confidence in Medical QA Short 7 页 · PDF
161 Can AI Be a Good Peer Reviewer? A Survey of Peer Review Process, Evaluation, and the Future Long 7 页 · PDF
162 Can AI-Generated Persuasion Be Detected? Persuaficial Benchmark and AI vs. Human Linguistic Differences Long 7 页 · PDF
163 Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streams Long 7 页 · PDF
164 Can LLMs Act as Historians? Evaluating Historical Research Capabilities of LLMs via the Chinese Imperial Examination Long 7 页 · PDF
165 CaseFacts: A Benchmark for Legal Fact-Checking and Precedent Retrieval Long 7 页 · PDF
166 Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models Long 7 页 · PDF
167 Chart-MRAG: Benchmarking Multimodal Retrieval Augmented Generation on Chart-based Documents Long 7 页 · PDF
168 ChessArena: A Chess Testbed for Evaluating Strategic Reasoning Capabilities of Large Language Models Long 7 页 · PDF
169 ChiKhaPo: A Large-Scale Multilingual Benchmark for Evaluating Lexical Comprehension and Generation in Large Language Models Long 7 页 · PDF
170 ClaimDB: A Fact Verification Benchmark over Large Structured Data Long 7 页 · PDF
171 CodeFlowBench: A Multi-turn, Iterative Benchmark for Complex Code Generation Long 7 页 · PDF
172 COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs Long 7 页 · PDF
173 CompTab: A Comprehensive Benchmark for Real-World TableQA with Complex Reasoning and Irregular Tables Long 7 页 · PDF
174 Confidence Should Be Calibrated More Than One Turn Deep Long 7 页 · PDF
175 CoQuIR: A Comprehensive Benchmark for Code Quality-Aware Information Retrieval Long 7 页 · PDF
176 CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents Long 7 页 · PDF
177 CT-FineBench: A Diagnostic Fidelity Benchmark for Fine-Grained Evaluation of CT Report Generation Long 7 页 · PDF
178 CUB: Benchmarking Context Utilisation Techniques for Language Models Long 7 页 · PDF
179 Cultural Benchmarking of LLMs in Standard and Dialectal Arabic Dialogues Long 7 页 · PDF
180 Culture-Aware Machine Translation in Large Language Models: Benchmarking and Investigation Long 7 页 · PDF
181 Dashboard2Code: Evaluating Multimodal Models on Reconstructing Interactive Dashboards Long 7 页 · PDF
182 Decoding Scientific Experimental Images: The SPUR Benchmark for Perception, Understanding, and Reasoning Long 7 页 · PDF
183 DetectRL-X: Towards Reliable Multilingual and Real-World LLM-Generated Text Detection Long 7 页 · PDF
184 DisCal: Distribution-Aware Calibration for Mathematical Reasoning Under Character-Level Noisy Inputs Long 7 页 · PDF
185 Diversity in Unity, Theory in Practice: Hierarchical Multitask Benchmarks for Chinese Minority Languages Long 7 页 · PDF
186 DIXITWORLD: Evaluating Multimodal Abductive Reasoning in Vision-Language Models with Multi-Agent Dixit Gameplay Short 7 页 · PDF
187 Do MLLMs Capture How Interfaces Guide User Behavior? A Benchmark for Multimodal UI/UX Design Understanding Long 7 页 · PDF
188 DRInQ: Evaluating Conversational Implicature with Controlled Context Variation Long 7 页 · PDF
189 EIFFEL: a novel benchmark to measure bias of English heavy training on French idiomatic expressions Long 7 页 · PDF
190 EmoHarbor: Evaluating Personalized Emotional Support by Simulating the User’s Internal World Long 7 页 · PDF
191 Evaluating Answer Leakage Robustness of LLM Tutors against Adversarial Student Attacks Long 7 页 · PDF
192 Evaluating Robustness of Large Language Models Against Multilingual Typographical Errors Long 7 页 · PDF
193 Evaluating Temporal Consistency in Multi-Turn Language Models Long 7 页 · PDF
194 Evaluating Visual Narrative Coherence in Story Visualization via Diversified Storylines Long 7 页 · PDF
195 EvolvR: Self-Evolving Pairwise Reasoning for Story Evaluation to Enhance Generation Long 7 页 · PDF
196 Explain the Synth: Interpretable Evaluation of LLM Data Synthesis Long 7 页 · PDF
197 FactVerse: A Benchmark for Factual Consistency in Interleaved Image–Text Generation Long 7 页 · PDF
198 From Charts to Code: A Hierarchical Benchmark for Multimodal Models Long 7 页 · PDF
199 G-IdiomAlign: A Gloss-Pivoted Benchmark for Cross-Lingual Idiom Alignment Long 7 页 · PDF
200 GameplayQA: A Benchmarking Framework for Decision-Dense POV-Synced Multi-Video Understanding of 3D Virtual Agents Long 7 页 · PDF
201 GeoArena: Evaluating Open-World Geographic Reasoning in Large Vision-Language Models Long 7 页 · PDF
202 GitChameleon 2.0: Evaluating AI Code Generation Against Python Library Version Incompatibilities Long 7 页 · PDF
203 GKnow: Measuring the Entanglement of Gender Bias and Factual Gender Long 7 页 · PDF
204 GROKE: Vision-Free Navigation Instruction Evaluation via Graph Reasoning on OpenStreetMap Long 7 页 · PDF
205 GroupToM-Bench: Benchmarking Group Theory of Mind and Nonlinear Social Emergence in MLLMs Long 7 页 · PDF
206 HalluAudio: A Comprehensive Benchmark for Hallucination Detection in Large Audio-Language Models Long 7 页 · PDF
207 HiChunk: Evaluating and Enhancing Retrieval Augmented Generation with Hierarchical Chunking Long 7 页 · PDF
208 How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities Long 7 页 · PDF
209 How Much Would a Clinician Edit This Draft? Evaluating LLM Alignment for Patient Message Response Drafting Long 7 页 · PDF
210 HowToNarrate: A General-Domain Benchmark for Synchronized Video Narration with External Knowledge Long 7 页 · PDF
211 If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMs Long 7 页 · PDF
212 ImplicitMemBench: Measuring Unconscious Behavioral Adaptation in Large Language Models Long 7 页 · PDF
213 INFACT: A Diagnostic Benchmark for Induced Faithfulness and Factuality Hallucinations in Video-LLMs Long 7 页 · PDF
214 InsLogicBench: An Argumentation Logic Grounded Benchmark for Complex Insurance Claims Adjudication Long 7 页 · PDF
215 Interpretable Coreference Resolution Evaluation Using Explicit Semantics Long 7 页 · PDF
216 It’s Not What You Say, It’s How You Say It: Evaluating LLM Responses to Expressions of Belief Long 7 页 · PDF
217 JanusMM: A Benchmark for Self-Deprecation Understanding in Real-World Multimodal Conversations Long 7 页 · PDF
218 KG-MuLQA: A Framework for KG-based Multi-Level QA Extraction and Long-Context LLM Evaluation Long 7 页 · PDF
219 Knowledge Beyond Language: Bridging the Gap in Multilingual Machine Unlearning Evaluation Long 7 页 · PDF
220 KnowMe-Bench: Benchmarking Person Understanding for Lifelong Digital Companions Long 7 页 · PDF
221 Language Models Don’t Know What You Want: Evaluating Personalization in Deep Research Needs Real Users Long 7 页 · PDF
222 LeCoDe: A Benchmark Dataset for Interactive Legal Consultation Dialogue Evaluation Long 7 页 · PDF
223 LitVISTA: A Benchmark for Narrative Orchestration in Literary Text Long 7 页 · PDF
224 LiveCultureBench: a Multi-Agent, Multi-Cultural Benchmark for Large Language Models in Dynamic Social Simulations Long 7 页 · PDF
225 LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient Long 7 页 · PDF
226 LOGICAL-COMMONSENSEQA: A Benchmark for Logical Commonsense Reasoning Short 7 页 · PDF
227 LongTutor: Benchmarking Large Language Models for Long-term Personalized Tutoring Long 7 页 · PDF
228 Lost in the Mix: Evaluating LLM Understanding of Code-Switched Text Long 7 页 · PDF
229 Market-Bench: Benchmarking Large Language Models on Economic and Trade Competition Long 7 页 · PDF
230 MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents Long 7 页 · PDF
231 Measuring Human Contribution in AI-Assisted Content Generation Long 7 页 · PDF
232 Measuring What Matters!! Assessing Therapeutic Principles in Mental-Health Conversation Long 7 页 · PDF
233 MediEval: A Unified Medical Benchmark for Patient-Contextual and Knowledge-Grounded Reasoning in LLMs Long 7 页 · PDF
234 MedMCP-Calc: Benchmarking LLMs for Realistic Medical Calculator Scenarios via MCP Integration Long 7 页 · PDF
235 Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents Long 7 页 · PDF
236 Mem2ActBench: A Benchmark for Evaluating Long-Term Memory Utilization in Task-Oriented Autonomous Agents Long 7 页 · PDF
237 Mind’s Eye: A Benchmark of Visual Abstraction, Transformation and Composition for Multimodal LLMs Long 7 页 · PDF
238 MMAC: A Multilingual, Multimodal Alignment Framework for Cultural Grounding Evaluation Long 7 页 · PDF
239 MMErroR: A Benchmark for Erroneous Reasoning in Vision-Language Models Long 7 页 · PDF
240 MMSciCode: Real-world Evaluation of Multilingual Multi-Discipline Scientific Research Coding Long 7 页 · PDF
241 MMTutorBench: The First Multimodal Benchmark for AI Math Tutoring Long 7 页 · PDF
242 More Than Meets the Eye: Measuring the Semiotic Gap in Vision-Language Models via Semantic Anchorage Long 7 页 · PDF
243 MORPHOGEN: A Multilingual Benchmark for Evaluating Gender-Aware Morphological Generation Long 7 页 · PDF
244 MTAVG-Bench: A Diagnostic Benchmark for Multi-Talker Dialogue-Centric Audio-Video Generation Long 7 页 · PDF
245 MTR-Bench: A Comprehensive Benchmark for Multi-Turn Reasoning Evaluation Long 7 页 · PDF
246 MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application Long 7 页 · PDF
247 NL ⇒ Schedule: Evaluate Multitask Scheduling Capability of Large Language Models Long 7 页 · PDF
248 NoisyCausal: A Benchmark for Evaluating Causal Reasoning Under Structured Noise Long 7 页 · PDF
249 OMIBench: Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language Models Long 7 页 · PDF
250 One Battle After Another: Probing LLMs’ Limits on Multi-Turn Instruction Following with a Benchmark Evolving Framework Long 7 页 · PDF
251 Par-ITA: Benchmarking Seq2Seq and LLMs on a Human-Supervised Parallel Corpus for Italian Hyperpartisan Neutralization Long 7 页 · PDF
252 Perception, Understanding and Reasoning: A Multimodal Benchmark for Video Fake News Detection Long 7 页 · PDF
253 Phun-Bench: Evaluating LLMs on Phonological Understanding in Chinese Long 7 页 · PDF
254 PII-Bench: Evaluating Query-Aware Privacy Protection Systems Long 7 页 · PDF
255 PLAWBENCH: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice Long 7 页 · PDF
256 PolitNuggets: Benchmarking Agentic Discovery of Long-Tail Political Facts Long 7 页 · PDF
257 PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering Long 7 页 · PDF
258 Psychological Steering in LLMs: An Evaluation of Effectiveness and Trustworthiness Long 7 页 · PDF
259 Putting Captions to the Test: Evaluating Video Caption Quality through Multiple-Choice Question Answering Long 7 页 · PDF
260 Quantifying Aleatoric Uncertainty of In-Context Learning for Robust Measure of LLM Prediction Confidence Long 7 页 · PDF
261 RARE: Redundancy-Aware Retrieval Evaluation Framework for High-Similarity Corpora Long 7 页 · PDF
262 Ready Jurist One: Benchmarking Language Agents for Legal Intelligence in Dynamic Environments Long 7 页 · PDF
263 RepoGenesis: Benchmarking End-to-End Microservice Generation from Readme to Repository Long 7 页 · PDF
264 ReportLogic: Evaluating Logical Quality in Deep Research Reports Long 7 页 · PDF
265 Responsible Evaluation of AI for Mental Health Long 7 页 · PDF
266 Rethinking Composed Image Retrieval Evaluation: A Fine-Grained Benchmark from Image Editing Long 7 页 · PDF
267 Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems Long 7 页 · PDF
268 ReTRE: Benchmarking LLM Transfer Robustness with Structure-Preserving Variants Long 7 页 · PDF
269 Revisiting Evaluation of Question Answering Systems in Low-Resource Indic Languages: Bridging Human and Metric Alignment Short 7 页 · PDF
270 RPC-Bench: A Fine-grained Benchmark for Research Paper Comprehension Long 7 页 · PDF
271 Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Long 7 页 · PDF
272 SciCustom: A Framework for Custom Evaluation of Scientific Capabilities in Large Language Models Long 7 页 · PDF
273 SciFlow-Bench: Evaluating Structure-Aware Scientific Diagram Generation via Inverse Parsing Long 7 页 · PDF
274 SenseRel: A Sense-Level Benchmark for Denotational and Connotational Meaning Relations Long 7 页 · PDF
275 ServImage: An Image Generation and Editing Benchmark from Real-world Commercial Imaging Services Long 7 页 · PDF
276 SGVEF-LOOP: Coverage-Guided Progressive Topological Exploration and Fact-Grounded Metamorphic Evaluation for MCP Agents Long 7 页 · PDF
277 SMART: Evaluating LLMs’ Mathematical Reasoning via a Human Cognitive Process-Inspired Benchmark Long 7 页 · PDF
278 SpeakerSleuth: Can Large Audio-Language Models Judge Speaker Consistency across Multi-turn Dialogues? Long 7 页 · PDF
279 Stereotype Bias in a Bilingual Setting: A Culturally Grounded Evaluation in Kazakhstan Long 7 页 · PDF
280 StratMem-Bench: Evaluating Strategic Memory Use in Virtual Character Conversation Beyond Factual Recall Long 7 页 · PDF
281 Sycophants in the Courtroom: Are LLMs Fragile to Juridical Authority and Evolving Legal Standards? Long 7 页 · PDF
282 TAMAS: Benchmarking Adversarial Risks in Multi-Agent LLM Systems Long 7 页 · PDF
283 TEA-Bench: A Systematic Benchmarking of Tool-enhanced Emotional Support Dialogue Agent Long 7 页 · PDF
284 The GaoYao Benchmark: A Comprehensive Framework for Evaluating Multilingual and Multicultural Abilities of Large Language Models Long 7 页 · PDF
285 TPS-Bench: Evaluating AI Agents’ Tool Planning & Scheduling Abilities in Compounding Tasks Long 7 页 · PDF
286 Truth or Sophistry? LoFa: A Benchmark for LLM Robustness Against Logical Fallacies Long 7 页 · PDF
287 TwiUSD: A Benchmark Dataset and Structure-Aware LLM Framework for User Stance Detection Long 7 页 · PDF
288 Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark Long 7 页 · PDF
289 VALU: A Benchmark for Video Anomaly Temporal Localization and Understanding at Multiple Semantic Levels Long 7 页 · PDF
290 Video-MMMU: Evaluating Knowledge Acquisition from Multidisciplinary Professional Videos Long 7 页 · PDF
291 ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World Scenarios Long 7 页 · PDF
292 VIGNETTE: Socially Grounded Bias Evaluation for Vision-Language Models Long 7 页 · PDF
293 WebCoderBench: Benchmarking Web Application Generation with Comprehensive and Interpretable Evaluation Metrics Long 7 页 · PDF
294 When Bigger Isn’t Better: A Comprehensive Fairness Evaluation of Political Bias in Multi-News Summarisation Long 7 页 · PDF
295 When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors Long 7 页 · PDF
296 Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment Long 7 页 · PDF
297 A Shared Geometry of Difficulty in Multilingual Language Models Short 6 页 · PDF
298 AgentCoMa: A Compositional Benchmark Mixing Commonsense and Mathematical Reasoning in Real-World Scenarios Long 6 页 · PDF
299 AlignUSER: Human-Aligned LLM Agents via World Models for Recommender System Evaluation Long 6 页 · PDF
300 Among Us: Measuring and Mitigating Malicious Contributions in Model Collaboration Systems Long 6 页 · PDF

评论