{"total":53,"rows":[{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242,"area":null},{"id":"2110.08420","title":"Understanding Dataset Difficulty with $\\mathcal{V}$-Usable Information","created":"2021-10-16","cited_by_count":291,"area":null},{"id":"2207.13332","title":"RealTime QA: What's the Answer Right Now?","created":"2022-07-27","cited_by_count":244,"area":null},{"id":"2406.04244","title":"Benchmark Data Contamination of Large Language Models: A Survey","created":"2024-06-06","cited_by_count":147,"area":null},{"id":"2406.12373","title":"WebCanvas: Benchmarking Web Agents in Online Environments","created":"2024-06-18","cited_by_count":121,"area":"agents"},{"id":"2309.17167","title":"DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks","created":"2023-09-29","cited_by_count":101,"area":"lr"},{"id":"2402.14865","title":"Dynamic Evaluation of Large Language Models by Meta Probing Agents","created":"2024-02-21","cited_by_count":54,"area":"agents"},{"id":"2205.12586","title":"Perturbation Augmentation for Fairer NLP","created":"2022-05-25","cited_by_count":52,"area":null},{"id":"2108.05921","title":"Hatemoji: A Test Suite and Adversarially-Generated Dataset for Benchmarking and Detecting Emoji-based Hate","created":"2021-08-12","cited_by_count":50,"area":null},{"id":"2205.05092","title":"Problems with Cosine as a Measure of Embedding Similarity for High Frequency Words","created":"2022-05-10","cited_by_count":49,"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":"2206.09755","title":"Square One Bias in NLP: Towards a Multi-Dimensional Exploration of the Research Manifold","created":"2022-06-20","cited_by_count":29,"area":null},{"id":"2210.03070","title":"Toxicity in Multilingual Machine Translation at Scale","created":"2022-10-06","cited_by_count":26,"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":"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":"2205.12676","title":"Evaluating the Diversity, Equity and Inclusion of NLP Technology: A Case Study for Indian Languages","created":"2022-05-25","cited_by_count":20,"area":null},{"id":"2205.05071","title":"Towards Climate Awareness in NLP Research","created":"2022-05-10","cited_by_count":19,"area":null},{"id":"2204.11574","title":"A global analysis of metrics used for measuring performance in natural language processing","created":"2022-04-25","cited_by_count":17,"area":null},{"id":"2406.14230","title":"Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing","created":"2024-06-20","cited_by_count":17,"area":null},{"id":"2204.01906","title":"Dynatask: A Framework for Creating Dynamic AI Benchmark Tasks","created":"2022-04-05","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":"2210.05769","title":"Vote'n'Rank: Revision of Benchmarking with Social Choice Theory","created":"2022-10-11","cited_by_count":15,"area":null},{"id":"2210.07352","title":"Predicting Fine-Tuning Performance with Probing","created":"2022-10-13","cited_by_count":13,"area":null},{"id":"2506.03231","title":"NetArena: Dynamic Benchmarks for AI Agents in Network Automation","created":"2025-06-03","cited_by_count":9,"area":null},{"id":"2307.09701","title":"Efficiency Pentathlon: A Standardized Arena for Efficiency Evaluation","created":"2023-07-19","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":"2210.15037","title":"Generalization Differences between End-to-End and Neuro-Symbolic Vision-Language Reasoning Systems","created":"2022-10-26","cited_by_count":6,"area":null},{"id":"2206.04137","title":"Adversarial Text Normalization","created":"2022-06-08","cited_by_count":5,"area":null},{"id":"2310.13859","title":"Not all Fake News is Written: A Dataset and Analysis of Misleading Video Headlines","created":"2023-10-20","cited_by_count":5,"area":null},{"id":"2503.05049","title":"Dynamic-KGQA: A Scalable Framework for Generating Adaptive Question Answering Datasets","created":"2025-03-06","cited_by_count":5,"area":null},{"id":"2212.01340","title":"Moving Beyond Downstream Task Accuracy for Information Retrieval Benchmarking","created":"2022-12-02","cited_by_count":4,"area":null},{"id":"2306.02349","title":"bgGLUE: A Bulgarian General Language Understanding Evaluation Benchmark","created":"2023-06-04","cited_by_count":4,"area":null},{"id":"2506.15846","title":"Finance Language Model Evaluation (FLaME)","created":"2025-06-18","cited_by_count":4,"area":null},{"id":"2510.17725","title":"AcademicEval: Live Long-Context LLM Benchmark","created":"2025-10-20","cited_by_count":4,"area":null},{"id":"2506.21508","title":"skLEP: A Slovak General Language Understanding Benchmark","created":"2025-06-26","cited_by_count":3,"area":null},{"id":"2303.07272","title":"Inventing a coin-flip classifier: Accounting for multiplicity in machine learning benchmark performance","created":"2023-03-10","cited_by_count":2,"area":null},{"id":"2305.12951","title":"Cross-functional Analysis of Generalisation in Behavioural Learning","created":"2023-05-22","cited_by_count":2,"area":null},{"id":"2310.01448","title":"Meta Semantic Template for Evaluation of Large Language Models","created":"2023-10-01","cited_by_count":2,"area":null},{"id":"2503.04655","title":"CLDyB: Towards Dynamic Benchmarking for Continual Learning with Pre-trained Models","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2604.21769","title":"Who Defines \"Best\"? Towards Interactive, User-Defined Evaluation of LLM Leaderboards","created":"2026-04-23","cited_by_count":2,"area":null},{"id":"2606.17541","title":"Offline Preference-Based Trajectory Evaluation","created":"2026-06-16","cited_by_count":2,"area":"agents"},{"id":"2201.05026","title":"Fantastic Data and How to Query Them","created":"2022-01-13","cited_by_count":1,"area":null},{"id":"2205.06871","title":"Near-Negative Distinction: Giving a Second Life to Human Evaluation Datasets","created":"2022-05-13","cited_by_count":1,"area":null},{"id":"2305.15130","title":"On Degrees of Freedom in Defining and Testing Natural Language Understanding","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2311.15108","title":"Leveraging Diffusion Perturbations for Measuring Fairness in Computer Vision","created":"2023-11-25","cited_by_count":1,"area":"diffusion"},{"id":"2401.11185","title":"How the Advent of Ubiquitous Large Language Models both Stymie and Turbocharge Dynamic Adversarial Question Generation","created":"2024-01-20","cited_by_count":1,"area":null},{"id":"2603.04656","title":"iAgentBench: Benchmarking Sensemaking Capabilities of Information-Seeking Agents on High-Traffic Topics","created":"2026-03-04","cited_by_count":1,"area":"agents"},{"id":"2607.24573","title":"LLM-SoccerArena: Benchmarking LLMs on Real-World Predictions in Sports","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2505.12526","title":"Never Skip a Batch: Dense Learning of Temporal GNNs via Adaptive Pseudo-Supervision","created":"2025-05-18","cited_by_count":0,"area":null},{"id":"2507.17922","title":"From Seed to Harvest: Augmenting Human Creativity with AI for Red-teaming Text-to-Image Models","created":"2025-07-23","cited_by_count":0,"area":"safety"},{"id":"2608.09485","title":"Capability Is Not Propensity: Measuring Pressure-Robust Cooperative Behavior in Civic LLM Agents","created":"2026-08-10","cited_by_count":0,"area":"agents"},{"id":"2609.32109","title":"How Reusable Are Benchmarks with Richer Feedback?","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.35113","title":"SymbolicArena: A Unified Infrastructure for Benchmark Distillation and Dynamic Evaluation in Symbolic Regression","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}