{"total":203,"rows":[{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373,"area":null},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879,"area":null},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162,"area":"lr"},{"id":"2111.15366","title":"AI and the Everything in the Whole Wide World Benchmark","created":"2021-11-26","cited_by_count":349,"area":null},{"id":"2110.00976","title":"LexGLUE: A Benchmark Dataset for Legal Language Understanding in English","created":"2021-10-03","cited_by_count":310,"area":null},{"id":"2111.02840","title":"Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models","created":"2021-11-04","cited_by_count":232,"area":null},{"id":"2112.08608","title":"QuALITY: Question Answering with Long Input Texts, Yes!","created":"2021-12-16","cited_by_count":208,"area":null},{"id":"2201.05955","title":"WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation","created":"2022-01-16","cited_by_count":202,"area":null},{"id":"2104.06644","title":"Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little","created":"2021-04-14","cited_by_count":177,"area":null},{"id":"2202.06935","title":"Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text","created":"2022-02-14","cited_by_count":155,"area":null},{"id":"2112.03052","title":"Scaling Up Influence Functions","created":"2021-12-06","cited_by_count":132,"area":null},{"id":"2511.04703","title":"Measuring what Matters: Construct Validity in Large Language Model Benchmarks","created":"2025-11-03","cited_by_count":119,"area":null},{"id":"2105.09680","title":"KLUE: Korean Language Understanding Evaluation","created":"2021-05-20","cited_by_count":114,"area":null},{"id":"2310.15819","title":"Generative Language Models Exhibit Social Identity Biases","created":"2023-10-24","cited_by_count":111,"area":null},{"id":"2505.08638","title":"TRAIL: Trace Reasoning and Agentic Issue Localization","created":"2025-05-13","cited_by_count":104,"area":"lr"},{"id":"2306.04618","title":"Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations","created":"2023-06-07","cited_by_count":97,"area":null},{"id":"2109.01653","title":"CREAK: A Dataset for Commonsense Reasoning over Entity Knowledge","created":"2021-09-03","cited_by_count":88,"area":null},{"id":"2309.08638","title":"Anchor Points: Benchmarking Models with Much Fewer Examples","created":"2023-09-14","cited_by_count":86,"area":null},{"id":"2203.04592","title":"Mapping global dynamics of benchmark creation and saturation in artificial intelligence","created":"2022-03-09","cited_by_count":71,"area":null},{"id":"2311.10057","title":"The Song Describer Dataset: a Corpus of Audio Captions for Music-and-Language Evaluation","created":"2023-11-16","cited_by_count":68,"area":null},{"id":"2305.14938","title":"Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark","created":"2023-05-24","cited_by_count":63,"area":null},{"id":"2502.06559","title":"Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluation","created":"2025-02-10","cited_by_count":60,"area":null},{"id":"2404.02418","title":"Auxiliary task demands mask the capabilities of smaller language models","created":"2024-04-03","cited_by_count":54,"area":null},{"id":"2203.07228","title":"FairLex: A Multilingual Benchmark for Evaluating Fairness in Legal Text Processing","created":"2022-03-14","cited_by_count":49,"area":null},{"id":"2205.05256","title":"Evaluation Gaps in Machine Learning Practice","created":"2022-05-11","cited_by_count":49,"area":null},{"id":"2506.12286","title":"The SWE-Bench Illusion: When State-of-the-Art LLMs Remember Instead of Reason","created":"2025-06-14","cited_by_count":49,"area":"lr"},{"id":"2503.05336","title":"Toward an Evaluation Science for Generative AI Systems","created":"2025-03-07","cited_by_count":45,"area":null},{"id":"2403.01931","title":"VariErr NLI: Separating Annotation Error from Human Label Variation","created":"2024-03-04","cited_by_count":42,"area":null},{"id":"2306.03586","title":"Language acquisition: do children and language models follow similar learning stages?","created":"2023-06-06","cited_by_count":41,"area":null},{"id":"2507.02856","title":"Answer Matching Outperforms Multiple Choice for Language Model Evaluation","created":"2025-07-03","cited_by_count":41,"area":null},{"id":"2110.08300","title":"The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail","created":"2021-10-15","cited_by_count":38,"area":null},{"id":"2206.11249","title":"GEMv2: Multilingual NLG Benchmarking in a Single Line of Code","created":"2022-06-22","cited_by_count":36,"area":null},{"id":"2211.15458","title":"Validating Large Language Models with ReLM","created":"2022-11-21","cited_by_count":33,"area":null},{"id":"2112.09062","title":"Models in the Loop: Aiding Crowdworkers with Generative Annotation Assistants","created":"2021-12-16","cited_by_count":31,"area":null},{"id":"2503.07832","title":"RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Code","created":"2025-03-10","cited_by_count":30,"area":"lr"},{"id":"2110.07596","title":"Retrieval-guided Counterfactual Generation for QA","created":"2021-10-14","cited_by_count":29,"area":null},{"id":"2208.12852","title":"What Do NLP Researchers Believe? Results of the NLP Community Metasurvey","created":"2022-08-26","cited_by_count":28,"area":null},{"id":"2405.01719","title":"Inherent Trade-Offs between Diversity and Stability in Multi-Task Benchmarks","created":"2024-05-02","cited_by_count":28,"area":null},{"id":"2406.08723","title":"ECBD: Evidence-Centered Benchmark Design for NLP","created":"2024-06-13","cited_by_count":28,"area":null},{"id":"2305.09022","title":"It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performance","created":"2023-05-15","cited_by_count":26,"area":null},{"id":"2405.13622","title":"Automated Evaluation of Retrieval-Augmented Language Models with Task-Specific Exam Generation","created":"2024-05-22","cited_by_count":25,"area":"rag"},{"id":"2502.07077","title":"Multi-turn Evaluation of Anthropomorphic Behaviours in Large Language Models","created":"2025-02-10","cited_by_count":25,"area":null},{"id":"2110.08514","title":"Analyzing Dynamic Adversarial Training Data in the Limit","created":"2021-10-16","cited_by_count":24,"area":null},{"id":"2406.19232","title":"RuBLiMP: Russian Benchmark of Linguistic Minimal Pairs","created":"2024-06-27","cited_by_count":24,"area":null},{"id":"2209.13020","title":"Law Informs Code: A Legal Informatics Approach to Aligning Artificial Intelligence with Humans","created":"2022-09-14","cited_by_count":23,"area":null},{"id":"2210.01970","title":"Evaluate & Evaluation on the Hub: Better Best Practices for Data and Model Measurements","created":"2022-09-30","cited_by_count":22,"area":null},{"id":"2412.03597","title":"The Vulnerability of Language Model Benchmarks: Do They Accurately Reflect True LLM Performance?","created":"2024-12-02","cited_by_count":22,"area":null},{"id":"2405.01820","title":"Real Risks of Fake Data: Synthetic Data, Diversity-Washing and Consent Circumvention","created":"2024-05-03","cited_by_count":21,"area":null},{"id":"2603.13285","title":"Brittlebench: Quantifying LLM robustness via prompt sensitivity","created":"2026-02-27","cited_by_count":21,"area":null},{"id":"2302.13959","title":"Make Every Example Count: On the Stability and Utility of Self-Influence for Learning from Noisy NLP Datasets","created":"2023-02-27","cited_by_count":19,"area":null},{"id":"2106.09069","title":"Automatic Construction of Evaluation Suites for Natural Language Generation Datasets","created":"2021-06-16","cited_by_count":18,"area":null},{"id":"2111.06467","title":"SynthBio: A Case Study in Human-AI Collaborative Curation of Text Datasets","created":"2021-11-11","cited_by_count":18,"area":null},{"id":"2306.13651","title":"Bring Your Own Data! Self-Supervised Evaluation for Large Language Models","created":"2023-06-23","cited_by_count":17,"area":null},{"id":"2309.07822","title":"CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration","created":"2023-09-14","cited_by_count":17,"area":null},{"id":"2201.07040","title":"Benchmark datasets driving artificial intelligence development fail to capture the needs of medical professionals","created":"2022-01-18","cited_by_count":16,"area":null},{"id":"2210.03165","title":"A Theory of Dynamic Benchmarks","created":"2022-10-06","cited_by_count":16,"area":null},{"id":"2402.02675","title":"Verifiable evaluations of machine learning models using zkSNARKs","created":"2024-02-05","cited_by_count":16,"area":null},{"id":"2409.02257","title":"MMLU-Pro+: Evaluating Higher-Order Reasoning and Shortcut Learning in LLMs","created":"2024-09-03","cited_by_count":16,"area":"lr"},{"id":"2210.05769","title":"Vote'n'Rank: Revision of Benchmarking with Social Choice Theory","created":"2022-10-11","cited_by_count":15,"area":null},{"id":"2412.06745","title":"ONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended Capabilities","created":"2024-12-09","cited_by_count":15,"area":null},{"id":"2506.21521","title":"Potemkin Understanding in Large Language Models","created":"2025-06-26","cited_by_count":15,"area":null},{"id":"2604.24955","title":"BenchGuard: Who Guards the Benchmarks? Automated Auditing of LLM Agent Benchmarks","created":"2026-04-27","cited_by_count":15,"area":"agents"},{"id":"2304.00815","title":"Design Choices for Crowdsourcing Implicit Discourse Relations: Revealing the Biases Introduced by Task Design","created":"2023-04-03","cited_by_count":14,"area":null},{"id":"2605.12673","title":"Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack","created":"2026-05-12","cited_by_count":14,"area":null},{"id":"2202.05302","title":"Trust in AI: Interpretability is not necessary or sufficient, while black-box interaction is necessary and sufficient","created":"2022-02-10","cited_by_count":13,"area":null},{"id":"2506.13342","title":"Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers","created":"2025-06-16","cited_by_count":13,"area":null},{"id":"2510.01353","title":"MEMTRACK: Evaluating Long-Term Memory and State Tracking in Multi-Platform Dynamic Agent Environments","created":"2025-10-01","cited_by_count":13,"area":"agents"},{"id":"2601.03986","title":"Benchmark^2: Systematic Evaluation of LLM Benchmarks","created":"2026-01-07","cited_by_count":13,"area":null},{"id":"2105.01974","title":"Do Natural Language Explanations Represent Valid Logical Arguments? Verifying Entailment in Explainable NLI Gold Standards","created":"2021-05-05","cited_by_count":12,"area":null},{"id":"2111.08181","title":"Adversarially Constructed Evaluation Sets Are More Challenging, but May Not Be Fair","created":"2021-11-16","cited_by_count":12,"area":null},{"id":"2204.05151","title":"Metaethical Perspectives on 'Benchmarking' AI Ethics","created":"2022-04-11","cited_by_count":12,"area":null},{"id":"2107.13935","title":"Break, Perturb, Build: Automatic Perturbation of Reasoning Paths Through Question Decomposition","created":"2021-07-29","cited_by_count":11,"area":null},{"id":"2203.06342","title":"What Makes Reading Comprehension Questions Difficult?","created":"2022-03-12","cited_by_count":11,"area":null},{"id":"2210.12813","title":"TAPE: Assessing Few-shot Russian Language Understanding","created":"2022-10-23","cited_by_count":11,"area":null},{"id":"2407.09221","title":"Evaluating AI Evaluation: Perils and Prospects","created":"2024-07-12","cited_by_count":11,"area":null},{"id":"2204.06251","title":"Experimental Standards for Deep Learning in Natural Language Processing Research","created":"2022-04-13","cited_by_count":10,"area":null},{"id":"2209.00692","title":"Making Intelligence: Ethical Values in IQ and ML Benchmarks","created":"2022-09-01","cited_by_count":10,"area":null},{"id":"2402.19472","title":"Efficient Lifelong Model Evaluation in an Era of Rapid Progress","created":"2024-02-29","cited_by_count":10,"area":null},{"id":"2410.24100","title":"Benchmark Data Repositories for Better Benchmarking","created":"2024-10-31","cited_by_count":10,"area":null},{"id":"2508.09853","title":"STREAM (ChemBio): A Standard for Transparently Reporting Evaluations in AI Model Reports","created":"2025-08-13","cited_by_count":10,"area":null},{"id":"2210.06799","title":"Benchmarking Long-tail Generalization with Likelihood Splits","created":"2022-10-13","cited_by_count":9,"area":null},{"id":"2410.11672","title":"Leaving the barn door open for Clever Hans: Simple features predict LLM benchmark answers","created":"2024-10-15","cited_by_count":9,"area":null},{"id":"2505.22830","title":"What Has Been Lost with Synthetic Evaluation?","created":"2025-05-28","cited_by_count":9,"area":null},{"id":"2112.09237","title":"PECO: Examining Single Sentence Label Leakage in Natural Language Inference Datasets through Progressive Evaluation of Cluster Outliers","created":"2021-12-16","cited_by_count":8,"area":null},{"id":"2201.06777","title":"COPA-SSE: Semi-structured Explanations for Commonsense Reasoning","created":"2022-01-18","cited_by_count":8,"area":"lr"},{"id":"2509.04373","title":"Measuring Bias or Measuring the Task: Understanding the Brittle Nature of LLM Gender Biases","created":"2025-09-04","cited_by_count":8,"area":null},{"id":"2112.00086","title":"Dyna-bAbI: unlocking bAbI's potential with dynamic synthetic benchmarking","created":"2021-11-30","cited_by_count":7,"area":null},{"id":"2202.12603","title":"Language technology practitioners as language managers: arbitrating data bias and predictive bias in ASR","created":"2022-02-25","cited_by_count":7,"area":null},{"id":"2305.14384","title":"Adversarial Nibbler: A Data-Centric Challenge for Improving the Safety of Text-to-Image Models","created":"2023-05-22","cited_by_count":7,"area":null},{"id":"2305.14681","title":"Emergent inabilities? Inverse scaling over the course of pretraining","created":"2023-05-24","cited_by_count":7,"area":null},{"id":"2406.16342","title":"Is your benchmark truly adversarial? AdvScore: Evaluating Human-Grounded Adversarialness","created":"2024-06-24","cited_by_count":7,"area":null},{"id":"2503.19193","title":"Browsing Lost Unformed Recollections: A Benchmark for Tip-of-the-Tongue Search and Reasoning","created":"2025-03-24","cited_by_count":7,"area":null},{"id":"2603.16848","title":"Mediocrity is the key for LLM as a Judge Anchor Selection","created":"2026-03-17","cited_by_count":7,"area":null},{"id":"2208.08010","title":"ShortcutLens: A Visual Analytics Approach for Exploring Shortcuts in Natural Language Understanding Dataset","created":"2022-08-17","cited_by_count":6,"area":null},{"id":"2311.07424","title":"Hallucination Augmented Recitations for Language Models","created":"2023-11-13","cited_by_count":6,"area":null},{"id":"2311.09480","title":"Show Your Work with Confidence: Confidence Bands for Tuning Curves","created":"2023-11-16","cited_by_count":6,"area":null},{"id":"2511.14366","title":"ATLAS: A High-Difficulty, Multidisciplinary Benchmark for Frontier Scientific Reasoning","created":"2025-11-18","cited_by_count":6,"area":"lr"},{"id":"2602.18182","title":"Capabilities Ain't All You Need: Measuring Propensities in AI","created":"2026-02-20","cited_by_count":6,"area":null},{"id":"2311.09694","title":"Whispers of Doubt Amidst Echoes of Triumph in NLP Robustness","created":"2023-11-16","cited_by_count":5,"area":null},{"id":"2406.12165","title":"Statistical Uncertainty in Word Embeddings: GloVe-V","created":"2024-06-18","cited_by_count":5,"area":null}],"next_cursor":"100"}