EMNLP 2025 · 全部收录(315 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 | Morables: A Benchmark for Assessing Abstract Moral Reasoning in LLMs with Fables | Main | 7 | 页 · PDF |
| 152 | MUCAR: Benchmarking Multilingual Cross-Modal Ambiguity Resolution for Multimodal Large Language Models | Main | 7 | 页 · PDF |
| 153 | MultiLogicNMR(er): A Benchmark and Neural-Symbolic Framework for Non-monotonic Reasoning with Multiple Extensions | Main | 7 | 页 · PDF |
| 154 | NESTFUL: A Benchmark for Evaluating LLMs on Nested Sequences of API Calls | Main | 7 | 页 · PDF |
| 155 | OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain | Main | 7 | 页 · PDF |
| 156 | On the Same Wavelength? Evaluating Pragmatic Reasoning in Language Models across Broad Concepts | Main | 7 | 页 · PDF |
| 157 | OpenTuringBench: An Open-Model-based Benchmark and Framework for Machine-Generated Text Detection and Attribution | Main | 7 | 页 · PDF |
| 158 | PakBBQ: A Culturally Adapted Bias Benchmark for QA | Main | 7 | 页 · PDF |
| 159 | PatentScore: Multi-dimensional Evaluation of LLM-Generated Patent Claims | Main | 7 | 页 · PDF |
| 160 | QualBench: Benchmarking Chinese LLMs with Localized Professional Qualifications for Vertical Domain Evaluation | Main | 7 | 页 · PDF |
| 161 | Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs | Main | 7 | 页 · PDF |
| 162 | R2I-Bench: Benchmarking Reasoning-Driven Text-to-Image Generation | Main | 7 | 页 · PDF |
| 163 | Refusal-Aware Red Teaming: Exposing Inconsistency in Safety Evaluations | Main | 7 | 页 · PDF |
| 164 | ReMedy: Learning Machine Translation Evaluation from Human Preferences with Reward Modeling | Main | 7 | 页 · PDF |
| 165 | RoDEval: A Robust Word Sense Disambiguation Evaluation Framework for Large Language Models | Main | 7 | 页 · PDF |
| 166 | SATBench: Benchmarking LLMs’ Logical Reasoning via Automated Puzzle Generation from SAT Formulas | Main | 7 | 页 · PDF |
| 167 | Seeing Culture: A Benchmark for Visual Reasoning and Grounding | Main | 7 | 页 · PDF |
| 168 | SEPS: A Separability Measure for Robust Unlearning in LLMs | Main | 7 | 页 · PDF |
| 169 | Sequential-NIAH: A Needle-In-A-Haystack Benchmark for Extracting Sequential Needles from Long Contexts | Main | 7 | 页 · PDF |
| 170 | SPECS: Specificity-Enhanced CLIP-Score for Long Image Caption Evaluation | Main | 7 | 页 · PDF |
| 171 | SportReason: Evaluating Retrieval-Augmented Reasoning across Tables and Text for Sports Question Answering | Main | 7 | 页 · PDF |
| 172 | SQUAB: Evaluating LLM robustness to Ambiguous and Unanswerable Questions in Semantic Parsing | Main | 7 | 页 · PDF |
| 173 | STEER-BENCH: A Benchmark for Evaluating the Steerability of Large Language Models | Main | 7 | 页 · PDF |
| 174 | TableEval: A Real-World Benchmark for Complex, Multilingual, and Multi-Structured Table Question Answering | Main | 7 | 页 · PDF |
| 175 | TFDP: Token-Efficient Disparity Audits for Autoregressive LLMs via Single-Token Masked Evaluation | Main | 7 | 页 · PDF |
| 176 | The Good, the Bad and the Constructive: Automatically Measuring Peer Review’s Utility for Authors | Main | 7 | 页 · PDF |
| 177 | The State of Multilingual LLM Safety Research: From Measuring The Language Gap To Mitigating It | Main | 7 | 页 · PDF |
| 178 | Think Globally, Group Locally: Evaluating LLMs Using Multi-Lingual Word Grouping Games | Main | 7 | 页 · PDF |
| 179 | TLUE: A Tibetan Language Understanding Evaluation Benchmark | Main | 7 | 页 · PDF |
| 180 | TounsiBench: Benchmarking Large Language Models for Tunisian Arabic | Main | 7 | 页 · PDF |
| 181 | Toxicity Red-Teaming: Benchmarking LLM Safety in Singapore’s Low-Resource Languages | Main | 7 | 页 · PDF |
| 182 | TP-RAG: Benchmarking Retrieval-Augmented Large Language Model Agents for Spatiotemporal-Aware Travel Planning | Main | 7 | 页 · PDF |
| 183 | TracSum: A New Benchmark for Aspect-Based Summarization with Sentence-Level Traceability in Medical Domain | Main | 7 | 页 · PDF |
| 184 | Transitive self-consistency evaluation of NLI models without gold labels | Main | 7 | 页 · PDF |
| 185 | Trojsten Benchmark: Evaluating LLM Problem-Solving in Slovak STEM Competition Problems | Main | 7 | 页 · PDF |
| 186 | TurBLiMP: A Turkish Benchmark of Linguistic Minimal Pairs | Main | 7 | 页 · PDF |
| 187 | TurnaboutLLM: A Deductive Reasoning Benchmark from Detective Games | Main | 7 | 页 · PDF |
| 188 | TVQACML: Benchmarking Text-Centric Visual Question Answering in Multilingual Chinese Minority Languages | Main | 7 | 页 · PDF |
| 189 | UNCLE: Benchmarking Uncertainty Expressions in Long-Form Generation | Main | 7 | 页 · PDF |
| 190 | Unmasking Deceptive Visuals: Benchmarking Multimodal Large Language Models on Misleading Chart Question Answering | Main | 7 | 页 · PDF |
| 191 | VisBias: Measuring Explicit and Implicit Social Biases in Vision Language Models | Main | 7 | 页 · PDF |
| 192 | VisEscape: A Benchmark for Evaluating Exploration-driven Decision-making in Virtual Escape Rooms | Main | 7 | 页 · PDF |
| 193 | WangchanThaiInstruct: An instruction-following Dataset for Culture-Aware, Multitask, and Multi-domain Evaluation in Thai | Main | 7 | 页 · PDF |
| 194 | Why Stop at One Error? Benchmarking LLMs as Data Science Code Debuggers for Multi-Hop and Multi-Bug Errors | Main | 7 | 页 · PDF |
| 195 | WildDoc: How Far Are We from Achieving Comprehensive and Robust Document Understanding in the Wild? | Main | 7 | 页 · PDF |
| 196 | WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning | Main | 7 | 页 · PDF |
| 197 | A Comprehensive Framework to Operationalize Social Stereotypes for Responsible AI Evaluations | Main | 6 | 页 · PDF |
| 198 | A Multi-Level Benchmark for Causal Language Understanding in Social Media Discourse | Main | 6 | 页 · PDF |
| 199 | A Rigorous Evaluation of LLM Data Generation Strategies for Low-Resource Languages | Main | 6 | 页 · PDF |
| 200 | AcT2I: Evaluating and Improving Action Depiction in Text-to-Image Models | Main | 6 | 页 · PDF |
| 201 | AraEval: An Arabic Multi-Task Evaluation Suite for Large Language Models | Main | 6 | 页 · PDF |
| 202 | ArgCMV: An Argument Summarization Benchmark for the LLM-era | Main | 6 | 页 · PDF |
| 203 | AssoCiAm: A Benchmark for Evaluating Association Thinking while Circumventing Ambiguity | Main | 6 | 页 · PDF |
| 204 | Benchmarking LLMs on Semantic Overlap Summarization | Main | 6 | 页 · PDF |
| 205 | Beyond the Leaderboard: Understanding Performance Disparities in Large Language Models via Model Diffing | Main | 6 | 页 · PDF |
| 206 | Bias Mitigation or Cultural Commonsense? Evaluating LLMs with a Japanese Dataset | Main | 6 | 页 · PDF |
| 207 | Calibrating LLM Confidence by Probing Perturbed Representation Stability | Main | 6 | 页 · PDF |
| 208 | Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations | Main | 6 | 页 · PDF |
| 209 | CHENGYU-BENCH: Benchmarking Large Language Models for Chinese Idiom Understanding and Use | Main | 6 | 页 · PDF |
| 210 | CMedCalc-Bench: A Fine-Grained Benchmark for Chinese Medical Calculations in LLM | Main | 6 | 页 · PDF |
| 211 | CodeMixBench: Evaluating Code-Mixing Capabilities of LLMs Across 18 Languages | Main | 6 | 页 · PDF |
| 212 | COM-BOM: Bayesian Exemplar Search for Efficiently Exploring the Accuracy-Calibration Pareto Frontier | Main | 6 | 页 · PDF |
| 213 | Context is Gold to find the Gold Passage: Evaluating and Training Contextual Document Embeddings | Main | 6 | 页 · PDF |
| 214 | CoVoGER: A Multilingual Multitask Benchmark for Speech-to-text Generative Error Correction with Large Language Models | Main | 6 | 页 · PDF |
| 215 | CRITICTOOL: Evaluating Self-Critique Capabilities of Large Language Models in Tool-Calling Error Scenarios | Main | 6 | 页 · PDF |
| 216 | DMDTEval: An Evaluation and Analysis of LLMs on Disambiguation in Multi-domain Translation | Main | 6 | 页 · PDF |
| 217 | DRISHTIKON: A Multimodal Multilingual Benchmark for Testing Language Models’ Understanding on Indian Culture | Main | 6 | 页 · PDF |
| 218 | EduVidQA: Generating and Evaluating Long-form Answers to Student Questions based on Lecture Videos | Main | 6 | 页 · PDF |
| 219 | Evaluating Behavioral Alignment in Conflict Dialogue: A Multi-Dimensional Comparison of LLM Agents and Humans | Main | 6 | 页 · PDF |
| 220 | Evaluating Robustness of Large Audio Language Models to Audio Injection: An Empirical Study | Main | 6 | 页 · PDF |
| 221 | Evaluating Taxonomy Free Character Role Labeling (TF-CRL) in News Stories using Large Language Models | Main | 6 | 页 · PDF |
| 222 | FacLens: Transferable Probe for Foreseeing Non-Factuality in Fact-Seeking Question Answering of Large Language Models | Main | 6 | 页 · PDF |
| 223 | FedMABench: Benchmarking Mobile GUI Agents on Decentralized Heterogeneous User Data | Main | 6 | 页 · PDF |
| 224 | FinMTEB: Finance Massive Text Embedding Benchmark | Main | 6 | 页 · PDF |
| 225 | FinTrust: A Comprehensive Benchmark of Trustworthiness Evaluation in Finance Domain | Main | 6 | 页 · PDF |
| 226 | FLUID QA: A Multilingual Benchmark for Figurative Language Usage in Dialogue across English, Chinese, and Korean | Main | 6 | 页 · PDF |
| 227 | FoREST: Frame of Reference Evaluation in Spatial Reasoning Tasks | Main | 6 | 页 · PDF |
| 228 | From Word to World: Evaluate and Mitigate Culture Bias in LLMs via Word Association Test | Main | 6 | 页 · PDF |
| 229 | Hanfu-Bench: A Multimodal Benchmark on Cross-Temporal Cultural Understanding and Transcreation | Main | 6 | 页 · PDF |
| 230 | Improve LLM-as-a-Judge Ability as a General Ability | Main | 6 | 页 · PDF |
| 231 | Keep Security! Benchmarking Security Policy Preservation in Large Language Model Contexts Against Indirect Attacks in Question Answering | Main | 6 | 页 · PDF |
| 232 | KRETA: A Benchmark for Korean Reading and Reasoning in Text-Rich VQA Attuned to Diverse Visual Contexts | Main | 6 | 页 · PDF |
| 233 | Let’s Play Across Cultures: A Large Multilingual, Multicultural Benchmark for Assessing Language Models’ Understanding of Sports | Main | 6 | 页 · PDF |
| 234 | LiTransProQA: An LLM-based Literary Translation Evaluation Metric with Professional Question Answering | Main | 6 | 页 · PDF |
| 235 | M-LongDoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework | Main | 6 | 页 · PDF |
| 236 | M3Retrieve: Benchmarking Multimodal Retrieval for Medicine | Main | 6 | 页 · PDF |
| 237 | Matter-of-Fact: A Benchmark for Verifying the Feasibility of Literature-Supported Claims in Materials Science | Main | 6 | 页 · PDF |
| 238 | MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models | Main | 6 | 页 · PDF |
| 239 | MULTIVOX: A Benchmark for Evaluating Voice Assistants for Multimodal Interactions | Main | 6 | 页 · PDF |
| 240 | NitiBench: Benchmarking LLM Frameworks on Thai Legal Question Answering Capabilities | Main | 6 | 页 · PDF |
| 241 | OntologyRAG-Q: Resource Development and Benchmarking for Retrieval-Augmented Question Answering in Qur’anic Tafsir | Main | 6 | 页 · PDF |
| 242 | P-MMEval: A Parallel Multilingual Multitask Benchmark for Consistent Evaluation of LLMs | Main | 6 | 页 · PDF |
| 243 | Persona-Augmented Benchmarking: Evaluating LLMs Across Diverse Writing Styles | Main | 6 | 页 · PDF |
| 244 | PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides | Main | 6 | 页 · PDF |
| 245 | PSET: a Phonetics-Semantics Evaluation Testbed | Main | 6 | 页 · PDF |
| 246 | PunMemeCN: A Benchmark to Explore Vision-Language Models’ Understanding of Chinese Pun Memes | Main | 6 | 页 · PDF |
| 247 | RAG-Zeval: Enhancing RAG Responses Evaluator through End-to-End Reasoning and Ranking-Based Reinforcement Learning | Main | 6 | 页 · PDF |
| 248 | RedHerring Attack: Testing the Reliability of Attack Detection | Main | 6 | 页 · PDF |
| 249 | SciEvent: Benchmarking Multi-domain Scientific Event Extraction | Main | 6 | 页 · PDF |
| 250 | Sentence Smith: Controllable Edits for Evaluating Text Embeddings | Main | 6 | 页 · PDF |
| 251 | Should I Share this Translation? Evaluating Quality Feedback for User Reliance on Machine Translation | Main | 6 | 页 · PDF |
| 252 | SinhalaMMLU: A Comprehensive Benchmark for Evaluating Multitask Language Understanding in Sinhala | Main | 6 | 页 · PDF |
| 253 | Sparse Activation Editing for Reliable Instruction Following in Narratives | Main | 6 | 页 · PDF |
| 254 | Structured Moral Reasoning in Language Models: A Value-Grounded Evaluation Framework | Main | 6 | 页 · PDF |
| 255 | T2R-BENCH: A Benchmark for Real World Table-to-Report Task | Main | 6 | 页 · PDF |
| 256 | Text2Vis: A Challenging and Diverse Benchmark for Generating Multimodal Visualizations from Text | Main | 6 | 页 · PDF |
| 257 | Thought calibration: Efficient and confident test-time scaling | Main | 6 | 页 · PDF |
| 258 | TurnBack: A Geospatial Route Cognition Benchmark for Large Language Models through Reverse Route | Main | 6 | 页 · PDF |
| 259 | VisFinEval: A Scenario-Driven Chinese Multimodal Benchmark for Holistic Financial Understanding | Main | 6 | 页 · PDF |
| 260 | WebMMU: A Benchmark for Multimodal Multilingual Website Understanding and Code Generation | Main | 6 | 页 · PDF |
| 261 | Benchmarking LLMs for Translating Classical Chinese Poetry: Evaluating Adequacy, Fluency, and Elegance | Main | 5 | 页 · PDF |
| 262 | Can LLMs be Good Graph Judge for Knowledge Graph Construction? | Main | 5 | 页 · PDF |
| 263 | ChartMind: A Comprehensive Benchmark for Complex Real-world Multimodal Chart Question Answering | Main | 5 | 页 · PDF |
| 264 | CLLMate: A Multimodal Benchmark for Weather and Climate Events Forecasting | Main | 5 | 页 · PDF |
| 265 | CMHG: A Dataset and Benchmark for Headline Generation of Minority Languages in China | Main | 5 | 页 · PDF |
| 266 | CodeArena: Evaluating and Aligning CodeLLMs on Human Preference | Main | 5 | 页 · PDF |
| 267 | Demystifying Synthetic Data in LLM Pre-training: A Systematic Study of Scaling Laws, Benefits, and Pitfalls | Main | 5 | 页 · PDF |
| 268 | EduAdapt: A Question Answer Benchmark Dataset for Evaluating Grade-Level Adaptability in LLMs | Main | 5 | 页 · PDF |
| 269 | EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language Models | Main | 5 | 页 · PDF |
| 270 | ESGenius: Benchmarking LLMs on Environmental, Social, and Governance (ESG) and Sustainability Knowledge | Main | 5 | 页 · PDF |
| 271 | Evaluating and Aligning Human Economic Risk Preferences in LLMs | Main | 5 | 页 · PDF |
| 272 | Evaluating Large Language Models for Detecting Antisemitism | Main | 5 | 页 · PDF |
| 273 | Evaluating the Effectiveness and Scalability of LLM-Based Data Augmentation for Retrieval | Main | 5 | 页 · PDF |
| 274 | From Capabilities to Performance: Evaluating Key Functional Properties of LLM Architectures in Penetration Testing | Main | 5 | 页 · PDF |
| 275 | Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewards | Main | 5 | 页 · PDF |
| 276 | KGE Calibrator: An Efficient Probability Calibration Method of Knowledge Graph Embedding Models for Trustworthy Link Prediction | Main | 5 | 页 · PDF |
| 277 | Large Language Models for Automated Literature Review: An Evaluation of Reference Generation, Abstract Writing, and Review Composition | Main | 5 | 页 · PDF |
| 278 | MA-DPR: Manifold-aware Distance Metrics for Dense Passage Retrieval | Main | 5 | 页 · PDF |
| 279 | Measuring and Mitigating Media Outlet Name Bias in Large Language Models | Main | 5 | 页 · PDF |
| 280 | Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge | Main | 5 | 页 · PDF |
| 281 | MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation | Main | 5 | 页 · PDF |
| 282 | Plutus: Benchmarking Large Language Models in Low-Resource Greek Finance | Main | 5 | 页 · PDF |
| 283 | PricingLogic: Evaluating LLMs Reasoning on Complex Tourism Pricing Tasks | Main | 5 | 页 · PDF |
| 284 | SciNLP: A Domain-Specific Benchmark for Full-Text Scientific Entity and Relation Extraction in NLP | Main | 5 | 页 · PDF |
| 285 | SolEval: Benchmarking Large Language Models for Repository-level Solidity Smart Contract Generation | Main | 5 | 页 · PDF |
| 286 | The Pursuit of Empathy: Evaluating Small Language Models for PTSD Dialogue Support | Main | 5 | 页 · PDF |
| 287 | Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey | Main | 5 | 页 · PDF |
| 288 | Understanding LLMs’ Cross-Lingual Context Retrieval: How Good It Is And Where It Comes From | Main | 5 | 页 · PDF |
| 289 | VEHME: A Vision-Language Model For Evaluating Handwritten Mathematics Expressions | Main | 5 | 页 · PDF |
| 290 | 3DS: Medical Domain Adaptation of LLMs via Decomposed Difficulty-based Data Selection | Main | 4 | 页 · PDF |
| 291 | Alignment Quality Index (AQI) : Beyond Refusals: AQI as an Intrinsic Alignment Diagnostic via Latent Geometry, Cluster Divergence, and Layer wise Pooled Representations | Main | 4 | 页 · PDF |
| 292 | Artificial Impressions: Evaluating Large Language Model Behavior Through the Lens of Trait Impressions | Main | 4 | 页 · PDF |
| 293 | Deriving Strategic Market Insights with Large Language Models: A Benchmark for Forward Counterfactual Generation | Main | 4 | 页 · PDF |
| 294 | Evaluating Cognitive-Behavioral Fixation via Multimodal User Viewing Patterns on Social Media | Main | 4 | 页 · PDF |
| 295 | Evaluation and Facilitation of Online Discussions in the LLM Era: A Survey | Main | 4 | 页 · PDF |
| 296 | How do Language Models Reshape Entity Alignment? A Survey of LM-Driven EA Methods: Advances, Benchmarks, and Future | Main | 4 | 页 · PDF |
| 297 | iTool: Reinforced Fine-Tuning with Dynamic Deficiency Calibration for Advanced Tool Use | Main | 4 | 页 · PDF |
| 298 | LLM-Driven Completeness and Consistency Evaluation for Cultural Heritage Data Augmentation in Cross-Modal Retrieval | Main | 4 | 页 · PDF |
| 299 | Mapping semantic networks to Dutch word embeddings as a diagnostic tool for cognitive decline | Main | 4 | 页 · PDF |
| 300 | Reliable and Cost-Effective Exploratory Data Analysis via Graph-Guided RAG | Main | 4 | 页 · PDF |