{"list":"other","total":51,"rows":[{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"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":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"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":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"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":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"2005.14050","title":"Language (Technology) is Power: A Critical Survey of \"Bias\" in NLP","created":"2020-05-28","cited_by_count":956},{"id":"2004.09456","title":"StereoSet: Measuring stereotypical bias in pretrained language models","created":"2020-04-20","cited_by_count":924},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743},{"id":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701},{"id":"1808.07042","title":"CoQA: A Conversational Question Answering Challenge","created":"2018-08-21","cited_by_count":683},{"id":"1910.11856","title":"On the Cross-lingual Transferability of Monolingual Representations","created":"2019-10-25","cited_by_count":578},{"id":"1804.09301","title":"Gender Bias in Coreference Resolution","created":"2018-04-25","cited_by_count":442},{"id":"2101.11718","title":"BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation","created":"2021-01-27","cited_by_count":412},{"id":"2111.15366","title":"AI and the Everything in the Whole Wide World Benchmark","created":"2021-11-26","cited_by_count":349},{"id":"1906.08976","title":"Mitigating Gender Bias in Natural Language Processing: Literature Review","created":"2019-06-21","cited_by_count":287},{"id":"2111.07997","title":"Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection","created":"2021-11-15","cited_by_count":264},{"id":"2012.05345","title":"Data and its (dis)contents: A survey of dataset development and use in machine learning research","created":"2020-12-09","cited_by_count":260},{"id":"1805.04508","title":"Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems","created":"2018-05-11","cited_by_count":234},{"id":"2104.02145","title":"What Will it Take to Fix Benchmarking in Natural Language Understanding?","created":"2021-04-05","cited_by_count":203},{"id":"2105.04054","title":"Societal Biases in Language Generation: Progress and Challenges","created":"2021-05-10","cited_by_count":202},{"id":"1901.10002","title":"A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle","created":"2019-01-28","cited_by_count":193},{"id":"1908.07898","title":"Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets","created":"2019-08-21","cited_by_count":175},{"id":"2106.15590","title":"The Values Encoded in Machine Learning Research","created":"2021-06-29","cited_by_count":172},{"id":"1808.07231","title":"Reducing Gender Bias in Abusive Language Detection","created":"2018-08-22","cited_by_count":152},{"id":"2010.13561","title":"Towards Accountability for Machine Learning Datasets: Practices from Software Engineering and Infrastructure","created":"2020-10-23","cited_by_count":138},{"id":"2209.07572","title":"Power to the People? Opportunities and Challenges for Participatory AI","created":"2022-09-15","cited_by_count":138},{"id":"1912.11078","title":"Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview","created":"2019-11-09","cited_by_count":137},{"id":"2411.12990","title":"BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices","created":"2024-11-20","cited_by_count":114},{"id":"2207.04108","title":"ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linking","created":"2022-07-08","cited_by_count":74},{"id":"2307.16778","title":"KoBBQ: Korean Bias Benchmark for Question Answering","created":"2023-07-31","cited_by_count":71},{"id":"1912.08320","title":"Garbage In, Garbage Out? Do Machine Learning Application Papers in Social Computing Report Where Human-Labeled Training Data Comes From?","created":"2019-12-17","cited_by_count":64},{"id":"2502.00561","title":"Position: Evaluating Generative AI Systems Is a Social Science Measurement Challenge","created":"2025-02-01","cited_by_count":63},{"id":"2306.06826","title":"When Do Annotator Demographics Matter? Measuring the Influence of Annotator Demographics with the POPQUORN Dataset","created":"2023-06-12","cited_by_count":52},{"id":"2106.01601","title":"Men Are Elected, Women Are Married: Events Gender Bias on Wikipedia","created":"2021-06-03","cited_by_count":30},{"id":"2411.10939","title":"Evaluating Generative AI Systems is a Social Science Measurement Challenge","created":"2024-11-17","cited_by_count":23},{"id":"2408.11441","title":"Epistemic Injustice in Generative AI","created":"2024-08-21","cited_by_count":16},{"id":"2409.11149","title":"SAGED: A Holistic Bias-Benchmarking Pipeline for Language Models with Customisable Fairness Calibration","created":"2024-09-17","cited_by_count":6},{"id":"2410.11059","title":"Assessing Bias in Metric Models for LLM Open-Ended Generation Bias Benchmarks","created":"2024-10-14","cited_by_count":4}],"next_cursor":null}