{"list":"other","total":68,"rows":[{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"1802.03426","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","created":"2018-02-09","cited_by_count":2898},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2207.04672","title":"No Language Left Behind: Scaling Human-Centered Machine Translation","created":"2022-07-11","cited_by_count":1312},{"id":"2311.07911","title":"Instruction-Following Evaluation for Large Language Models","created":"2023-11-14","cited_by_count":1228},{"id":"2209.07858","title":"Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned","created":"2022-08-23","cited_by_count":729},{"id":"2504.12516","title":"BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents","created":"2025-04-16","cited_by_count":647},{"id":"2411.04368","title":"Measuring short-form factuality in large language models","created":"2024-11-07","cited_by_count":373},{"id":"2311.11944","title":"FinanceBench: A New Benchmark for Financial Question Answering","created":"2023-11-20","cited_by_count":270},{"id":"2411.04872","title":"FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI","created":"2024-11-07","cited_by_count":243},{"id":"2004.03329","title":"MedDialog: Two Large-scale Medical Dialogue Datasets","created":"2020-04-07","cited_by_count":161},{"id":"1911.01547","title":"On the Measure of Intelligence","created":"2019-11-05","cited_by_count":144},{"id":"2402.12348","title":"GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations","created":"2024-02-19","cited_by_count":120},{"id":"2410.15553","title":"Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following","created":"2024-10-21","cited_by_count":102},{"id":"2311.02462","title":"Levels of AGI for Operationalizing Progress on the Path to AGI","created":"2023-11-04","cited_by_count":96},{"id":"2312.06281","title":"EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models","created":"2023-12-11","cited_by_count":80},{"id":"2311.08370","title":"SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Models","created":"2023-11-14","cited_by_count":76},{"id":"2505.23802","title":"MedHELM: Holistic Evaluation of Large Language Models for Medical Tasks","created":"2025-05-26","cited_by_count":64},{"id":"2509.07968","title":"SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge","created":"2025-09-09","cited_by_count":54},{"id":"2501.03200","title":"The FACTS Grounding Leaderboard: Benchmarking LLMs' Ability to Ground Responses to Long-Form Input","created":"2025-01-06","cited_by_count":52},{"id":"2104.06598","title":"AR-LSAT: Investigating Analytical Reasoning of Text","created":"2021-04-14","cited_by_count":51},{"id":"2310.05177","title":"Do Large Language Models Know about Facts?","created":"2023-10-08","cited_by_count":51},{"id":"2501.03468","title":"MTRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systems","created":"2025-01-07","cited_by_count":51},{"id":"2505.16944","title":"AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios","created":"2025-05-22","cited_by_count":49},{"id":"2505.15055","title":"Lost in Benchmarks? Rethinking Large Language Model Benchmarking with Item Response Theory","created":"2025-05-21","cited_by_count":45},{"id":"2306.10062","title":"Revealing the structure of language model capabilities","created":"2023-06-14","cited_by_count":40},{"id":"2503.11314","title":"Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering","created":"2025-03-14","cited_by_count":36},{"id":"2312.13951","title":"Typhoon: Thai Large Language Models","created":"2023-12-21","cited_by_count":30},{"id":"2410.02677","title":"CulturalBench: A Robust, Diverse, and Challenging Cultural Benchmark by Human-AI CulturalTeaming","created":"2024-10-03","cited_by_count":30},{"id":"2502.21228","title":"ECLeKTic: a Novel Challenge Set for Evaluation of Cross-Lingual Knowledge Transfer","created":"2025-02-28","cited_by_count":29},{"id":"2504.10356","title":"MultiLoKo: a multilingual local knowledge benchmark for LLMs spanning 31 languages","created":"2025-04-14","cited_by_count":26},{"id":"2309.06085","title":"BHASA: A Holistic Southeast Asian Linguistic and Cultural Evaluation Suite for Large Language Models","created":"2023-09-12","cited_by_count":18},{"id":"2512.10791","title":"The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factuality","created":"2025-12-11","cited_by_count":17},{"id":"2306.09237","title":"One Law, Many Languages: Benchmarking Multilingual Legal Reasoning for Judicial Support","created":"2023-06-15","cited_by_count":16},{"id":"2512.01992","title":"LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess","created":"2025-12-01","cited_by_count":15},{"id":"2104.08296","title":"Learning to Reason for Text Generation from Scientific Tables","created":"2021-04-16","cited_by_count":14},{"id":"2502.00595","title":"RPGBENCH: Evaluating Large Language Models as Role-Playing Game Engines","created":"2025-02-01","cited_by_count":12},{"id":"2509.16188","title":"CultureScope: A Dimensional Lens for Probing Cultural Understanding in LLMs","created":"2025-09-19","cited_by_count":12},{"id":"2408.00019","title":"WebApp1K: A Practical Code-Generation Benchmark for Web App Development","created":"2024-07-30","cited_by_count":11},{"id":"2510.24081","title":"Global PIQA: Evaluating Commonsense Reasoning Across 100+ Languages and Cultures","created":"2025-10-28","cited_by_count":10},{"id":"2602.24173","title":"LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics","created":"2026-02-27","cited_by_count":10},{"id":"2512.07795","title":"ReasonBENCH: Benchmarking the (In)Stability of LLM Reasoning","created":"2025-12-08","cited_by_count":9},{"id":"2507.21476","title":"Which LLMs Get the Joke? Probing Non-STEM Reasoning Abilities with HumorBench","created":"2025-07-29","cited_by_count":8},{"id":"2601.21448","title":"ChipBench: A Next-Step Benchmark for Evaluating LLM Performance in AI-Aided Chip Design","created":"2026-01-29","cited_by_count":8},{"id":"2510.23182","title":"SI-Bench: Benchmarking Social Intelligence of Large Language Models in Human-to-Human Conversations","created":"2025-10-27","cited_by_count":7},{"id":"2506.01819","title":"Not All Jokes Land: Evaluating Large Language Models Understanding of Workplace Humor","created":"2025-06-02","cited_by_count":6},{"id":"2509.23350","title":"ABC-Eval: Benchmarking Large Language Models on Symbolic Music Understanding and Instruction Following","created":"2025-09-27","cited_by_count":6},{"id":"2510.09517","title":"StatEval: A Comprehensive Benchmark for Large Language Models in Statistics","created":"2025-10-10","cited_by_count":6},{"id":"2501.17200","title":"Improving LLM Leaderboards with Psychometrical Methodology","created":"2025-01-27","cited_by_count":5},{"id":"2504.05898","title":"Assessing Thai Dialect Performance in LLMs with Automatic Benchmarks and Human Evaluation","created":"2025-04-08","cited_by_count":5},{"id":"2603.02540","title":"A Neuropsychologically Grounded Evaluation of LLM Cognitive Abilities","created":"2026-03-03","cited_by_count":5},{"id":"2602.15532","title":"Quantifying construct validity in large language model evaluations","created":"2026-02-17","cited_by_count":4},{"id":"2505.24826","title":"LegalEval-Q: A New Benchmark for The Quality Evaluation of LLM-Generated Legal Text","created":"2025-05-30","cited_by_count":3},{"id":"2510.13154","title":"The Alignment Veto: How Safety Training Suppresses Cultural Knowledge in LLMs","created":"2025-10-15","cited_by_count":3},{"id":"2601.14063","title":"XCR-Bench: Benchmarking Cross-Cultural Reasoning in LLMs via Culture-Specific Items and Hall's Triad","created":"2026-01-20","cited_by_count":3},{"id":"2605.25272","title":"AI Cartography: Mapping the Latent Landscape of AI Benchmark Ecosystems","created":"2026-05-24","cited_by_count":3},{"id":"2606.14516","title":"Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results","created":"2026-06-12","cited_by_count":3},{"id":"2410.22839","title":"Danoliteracy of Generative Large Language Models","created":"2024-10-30","cited_by_count":2},{"id":"2604.09911","title":"The Rise and Fall of $G$ in AGI","created":"2026-04-10","cited_by_count":2},{"id":"2410.07830","title":"NusaMT-7B: Machine Translation for Low-Resource Indonesian Languages with Large Language Models","created":"2024-10-10","cited_by_count":1},{"id":"2511.12387","title":"From Phonemes to Meaning: Evaluating Large Language Models on Tamil","created":"2025-11-15","cited_by_count":1},{"id":"2512.21494","title":"Oogiri-Master: Benchmarking Humor Understanding via Oogiri","created":"2025-12-25","cited_by_count":1},{"id":"2607.15587","title":"Rethinking Transfer in Continual Learning: A Replay-Based Realisation","created":"2026-07-17","cited_by_count":1}],"next_cursor":null}