{"list":"other","total":63,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"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":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"2210.03350","title":"Measuring and Narrowing the Compositionality Gap in Language Models","created":"2022-10-07","cited_by_count":1075},{"id":"2005.14050","title":"Language (Technology) is Power: A Critical Survey of \"Bias\" in NLP","created":"2020-05-28","cited_by_count":956},{"id":"1704.04683","title":"RACE: Large-scale ReAding Comprehension Dataset From Examinations","created":"2017-04-15","cited_by_count":861},{"id":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"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":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648},{"id":"2212.10403","title":"Towards Reasoning in Large Language Models: A Survey","created":"2022-12-20","cited_by_count":596},{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463},{"id":"1906.05317","title":"COMET: Commonsense Transformers for Automatic Knowledge Graph Construction","created":"2019-06-12","cited_by_count":450},{"id":"2402.07927","title":"A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications","created":"2024-02-05","cited_by_count":431},{"id":"1907.09693","title":"A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection","created":"2019-07-23","cited_by_count":374},{"id":"2312.14925","title":"A Survey of Reinforcement Learning from Human Feedback","created":"2023-12-22","cited_by_count":264},{"id":"2010.00711","title":"A Survey of the State of Explainable AI for Natural Language Processing","created":"2020-10-01","cited_by_count":206},{"id":"2004.10706","title":"CORD-19: The COVID-19 Open Research Dataset","created":"2020-04-22","cited_by_count":180},{"id":"2202.01110","title":"A Survey on Retrieval-Augmented Text Generation","created":"2022-02-02","cited_by_count":158},{"id":"2109.06157","title":"SituatedQA: Incorporating Extra-Linguistic Contexts into QA","created":"2021-09-13","cited_by_count":145},{"id":"2305.14536","title":"MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems","created":"2023-05-23","cited_by_count":131},{"id":"2105.04387","title":"Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey","created":"2021-05-10","cited_by_count":130},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130},{"id":"1905.04071","title":"Survey on Evaluation Methods for Dialogue Systems","created":"2019-05-10","cited_by_count":126},{"id":"2212.09746","title":"Evaluating Human-Language Model Interaction","created":"2022-12-19","cited_by_count":92},{"id":"2105.07190","title":"A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts","created":"2021-05-15","cited_by_count":91},{"id":"2203.01225","title":"Video Question Answering: Datasets, Algorithms and Challenges","created":"2022-03-02","cited_by_count":84},{"id":"2108.03362","title":"On Measures of Biases and Harms in NLP","created":"2021-08-07","cited_by_count":81},{"id":"2205.07540","title":"The AI Teacher Test: Measuring the Pedagogical Ability of Blender and GPT-3 in Educational Dialogues","created":"2022-05-16","cited_by_count":79},{"id":"2311.11797","title":"Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents","created":"2023-11-20","cited_by_count":72},{"id":"2202.07654","title":"Tomayto, Tomahto. Beyond Token-level Answer Equivalence for Question Answering Evaluation","created":"2022-02-15","cited_by_count":67},{"id":"2402.09369","title":"Massively Multi-Cultural Knowledge Acquisition & LM Benchmarking","created":"2024-02-14","cited_by_count":63},{"id":"2108.06688","title":"Complex Knowledge Base Question Answering: A Survey","created":"2021-08-15","cited_by_count":52},{"id":"2206.11309","title":"GODEL: Large-Scale Pre-Training for Goal-Directed Dialog","created":"2022-06-22","cited_by_count":51},{"id":"2404.01077","title":"Efficient Prompting Methods for Large Language Models: A Survey","created":"2024-04-01","cited_by_count":47},{"id":"1905.08949","title":"Recent Advances in Neural Question Generation","created":"2019-05-22","cited_by_count":42},{"id":"2008.03686","title":"Local Differential Privacy and Its Applications: A Comprehensive Survey","created":"2020-08-09","cited_by_count":41},{"id":"2207.05270","title":"A Survey on Table Question Answering: Recent Advances","created":"2022-07-12","cited_by_count":41},{"id":"2309.08591","title":"Are Multilingual LLMs Culturally-Diverse Reasoners? An Investigation into Multicultural Proverbs and Sayings","created":"2023-09-15","cited_by_count":32},{"id":"2402.09216","title":"AutoTutor meets Large Language Models: A Language Model Tutor with Rich Pedagogy and Guardrails","created":"2024-02-14","cited_by_count":31},{"id":"2302.11087","title":"A Survey on User Behavior Modeling in Recommender Systems","created":"2023-02-22","cited_by_count":26},{"id":"2305.14999","title":"The Art of SOCRATIC QUESTIONING: Recursive Thinking with Large Language Models","created":"2023-05-24","cited_by_count":22},{"id":"1909.02063","title":"The Diversity-Innovation Paradox in Science","created":"2019-09-04","cited_by_count":21},{"id":"2305.11033","title":"Visual Question Answering: A Survey on Techniques and Common Trends in Recent Literature","created":"2023-05-18","cited_by_count":21},{"id":"1909.01860","title":"Visual Question Answering using Deep Learning: A Survey and Performance Analysis","created":"2019-08-27","cited_by_count":19},{"id":"1608.09000","title":"Learning Syntactic Program Transformations from Examples","created":"2016-08-31","cited_by_count":17},{"id":"2206.05017","title":"Empathetic Conversational Systems: A Review of Current Advances, Gaps, and Opportunities","created":"2022-05-09","cited_by_count":14},{"id":"2305.12962","title":"Distilling ChatGPT for Explainable Automated Student Answer Assessment","created":"2023-05-22","cited_by_count":14},{"id":"1708.06564","title":"The Continuous Hint Factory - Providing Hints in Vast and Sparsely Populated Edit Distance Spaces","created":"2017-08-22","cited_by_count":12},{"id":"1908.11566","title":"A Survey of Automated Programming Hint Generation -- The HINTS Framework","created":"2019-08-30","cited_by_count":12},{"id":"2103.03125","title":"Advances in Multi-turn Dialogue Comprehension: A Survey","created":"2021-03-04","cited_by_count":12},{"id":"2105.08847","title":"Beyond \"Fairness:\" Structural (In)justice Lenses on AI for Education","created":"2021-05-18","cited_by_count":12},{"id":"2403.18426","title":"TriviaHG: A Dataset for Automatic Hint Generation from Factoid Questions","created":"2024-03-27","cited_by_count":7},{"id":"2110.10024","title":"Risks of AI Foundation Models in Education","created":"2021-10-19","cited_by_count":6},{"id":"2011.00192","title":"Personalized Multimodal Feedback Generation in Education","created":"2020-10-31","cited_by_count":4},{"id":"2105.05519","title":"Guiding Next-Step Hint Generation Using Automated Tests","created":"2021-05-12","cited_by_count":4},{"id":"2308.16349","title":"Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversations","created":"2023-08-30","cited_by_count":4},{"id":"2303.00146","title":"I Know Your Feelings Before You Do: Predicting Future Affective Reactions in Human-Computer Dialogue","created":"2023-03-01","cited_by_count":1}],"next_cursor":null}