{"list":"other","total":62,"rows":[{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"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":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2306.13394","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","created":"2023-06-23","cited_by_count":1652},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"2305.14251","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","created":"2023-05-23","cited_by_count":1282},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"2204.07705","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","created":"2022-04-16","cited_by_count":868},{"id":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701},{"id":"1712.07040","title":"The NarrativeQA Reading Comprehension Challenge","created":"2017-12-19","cited_by_count":597},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"2310.17623","title":"Proving Test Set Contamination in Black Box Language Models","created":"2023-10-26","cited_by_count":230},{"id":"2307.10928","title":"FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets","created":"2023-07-20","cited_by_count":201},{"id":"2311.04850","title":"Rethinking Benchmark and Contamination for Language Models with Rephrased Samples","created":"2023-11-08","cited_by_count":195},{"id":"2412.03304","title":"Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation","created":"2024-12-04","cited_by_count":191},{"id":"2406.09948","title":"BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages","created":"2024-06-14","cited_by_count":173},{"id":"2410.10989","title":"Liger Kernel: Efficient Triton Kernels for LLM Training","created":"2024-10-14","cited_by_count":130},{"id":"2411.12990","title":"BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices","created":"2024-11-20","cited_by_count":114},{"id":"2411.00860","title":"Survey of Cultural Awareness in Language Models: Text and Beyond","created":"2024-10-30","cited_by_count":103},{"id":"2404.15238","title":"CultureBank: An Online Community-Driven Knowledge Base Towards Culturally Aware Language Technologies","created":"2024-04-23","cited_by_count":98},{"id":"2309.04766","title":"SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoning","created":"2023-09-09","cited_by_count":94},{"id":"2402.11548","title":"KMMLU: Measuring Massive Multitask Language Understanding in Korean","created":"2024-02-18","cited_by_count":91},{"id":"2210.07763","title":"Extracting Cultural Commonsense Knowledge at Scale","created":"2022-10-14","cited_by_count":76},{"id":"2406.06565","title":"MixEval: Deriving Wisdom of the Crowd from LLM Benchmark Mixtures","created":"2024-06-03","cited_by_count":74},{"id":"2307.16778","title":"KoBBQ: Korean Bias Benchmark for Question Answering","created":"2023-07-31","cited_by_count":71},{"id":"2403.06412","title":"CLIcK: A Benchmark Dataset of Cultural and Linguistic Intelligence in Korean","created":"2024-03-11","cited_by_count":66},{"id":"2412.17259","title":"LegalAgentBench: Evaluating LLM Agents in Legal Domain","created":"2024-12-23","cited_by_count":59},{"id":"2406.04428","title":"MoralBench: Moral Evaluation of LLMs","created":"2024-06-06","cited_by_count":50},{"id":"2404.12464","title":"NormAd: A Framework for Measuring the Cultural Adaptability of Large Language Models","created":"2024-04-18","cited_by_count":48},{"id":"2309.02706","title":"HAE-RAE Bench: Evaluation of Korean Knowledge in Language Models","created":"2023-09-06","cited_by_count":47},{"id":"2503.05336","title":"Toward an Evaluation Science for Generative AI Systems","created":"2025-03-07","cited_by_count":45},{"id":"2501.02448","title":"Understand, Solve and Translate: Bridging the Multilingual Mathematical Reasoning Gap","created":"2025-01-05","cited_by_count":43},{"id":"2407.16711","title":"Benchmarks as Microscopes: A Call for Model Metrology","created":"2024-07-22","cited_by_count":35},{"id":"2402.13605","title":"KorNAT: LLM Alignment Benchmark for Korean Social Values and Common Knowledge","created":"2024-02-21","cited_by_count":33},{"id":"2406.17761","title":"CaLMQA: Exploring culturally specific long-form question answering across 23 languages","created":"2024-06-25","cited_by_count":31},{"id":"2406.11775","title":"Task Me Anything","created":"2024-06-17","cited_by_count":30},{"id":"2407.09823","title":"NativQA: Multilingual Culturally-Aligned Natural Query for LLMs","created":"2024-07-13","cited_by_count":30},{"id":"2503.14996","title":"Right Answer, Wrong Score: Uncovering the Inconsistencies of LLM Evaluation in Multiple-Choice Question Answering","created":"2025-03-19","cited_by_count":28},{"id":"2305.17701","title":"KoSBi: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Application","created":"2023-05-28","cited_by_count":24},{"id":"2403.01469","title":"KorMedMCQA: Multi-Choice Question Answering Benchmark for Korean Healthcare Professional Licensing Examinations","created":"2024-03-03","cited_by_count":22},{"id":"2504.01833","title":"YourBench: Easy Custom Evaluation Sets for Everyone","created":"2025-04-02","cited_by_count":20},{"id":"2305.01505","title":"Beyond Classification: Financial Reasoning in State-of-the-Art Language Models","created":"2023-04-30","cited_by_count":19},{"id":"2402.18045","title":"Multi-FAct: Assessing Factuality of Multilingual LLMs using FActScore","created":"2024-02-28","cited_by_count":18},{"id":"2409.02257","title":"MMLU-Pro+: Evaluating Higher-Order Reasoning and Shortcut Learning in LLMs","created":"2024-09-03","cited_by_count":16},{"id":"2406.10421","title":"SciEx: Benchmarking Large Language Models on Scientific Exams with Human Expert Grading and Automatic Grading","created":"2024-06-14","cited_by_count":14},{"id":"2410.24100","title":"Benchmark Data Repositories for Better Benchmarking","created":"2024-10-31","cited_by_count":10},{"id":"2412.07251","title":"KULTURE Bench: A Benchmark for Assessing Language Model in Korean Cultural Context","created":"2024-12-10","cited_by_count":8},{"id":"2410.08731","title":"Developing a Pragmatic Benchmark for Assessing Korean Legal Language Understanding in Large Language Models","created":"2024-10-11","cited_by_count":4},{"id":"2501.05712","title":"Multi-Step Reasoning in Korean and the Emergent Mirage","created":"2025-01-10","cited_by_count":4}],"next_cursor":null}