{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"2303.08896","title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models","created":"2023-03-15","cited_by_count":810},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763},{"id":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723},{"id":"2104.04473","title":"Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM","created":"2021-04-09","cited_by_count":632},{"id":"2302.11382","title":"A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT","created":"2023-02-21","cited_by_count":619},{"id":"2102.07350","title":"Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm","created":"2021-02-15","cited_by_count":606},{"id":"2303.11381","title":"MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action","created":"2023-03-20","cited_by_count":517},{"id":"2306.17492","title":"Preference Ranking Optimization for Human Alignment","created":"2023-06-30","cited_by_count":285},{"id":"2307.09009","title":"How is ChatGPT's behavior changing over time?","created":"2023-07-18","cited_by_count":270},{"id":"2307.10635","title":"SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models","created":"2023-07-20","cited_by_count":256},{"id":"2305.04790","title":"MultiModal-GPT: A Vision and Language Model for Dialogue with Humans","created":"2023-05-08","cited_by_count":255},{"id":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221},{"id":"2302.03494","title":"A Categorical Archive of ChatGPT Failures","created":"2023-02-06","cited_by_count":168},{"id":"1707.05589","title":"On the State of the Art of Evaluation in Neural Language Models","created":"2017-07-18","cited_by_count":104},{"id":"1811.02549","title":"Language GANs Falling Short","created":"2018-11-06","cited_by_count":97},{"id":"2004.10450","title":"Trading Off Diversity and Quality in Natural Language Generation","created":"2020-04-22","cited_by_count":96},{"id":"1909.10705","title":"Do Massively Pretrained Language Models Make Better Storytellers?","created":"2019-09-24","cited_by_count":90},{"id":"1801.01957","title":"From Eliza to XiaoIce: Challenges and Opportunities with Social Chatbots","created":"2018-01-06","cited_by_count":85},{"id":"1609.00150","title":"Reward Augmented Maximum Likelihood for Neural Structured Prediction","created":"2016-09-01","cited_by_count":81},{"id":"2203.08383","title":"Iteratively Prompt Pre-trained Language Models for Chain of Thought","created":"2022-03-16","cited_by_count":75},{"id":"2304.00612","title":"Eight Things to Know about Large Language Models","created":"2023-04-02","cited_by_count":73},{"id":"2208.07852","title":"Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Models","created":"2022-08-16","cited_by_count":70},{"id":"2107.06955","title":"HTLM: Hyper-Text Pre-Training and Prompting of Language Models","created":"2021-07-14","cited_by_count":58},{"id":"2112.07869","title":"Fine-Tuning Large Neural Language Models for Biomedical Natural Language Processing","created":"2021-12-15","cited_by_count":57},{"id":"1611.06256","title":"Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU","created":"2016-11-18","cited_by_count":48},{"id":"2305.14450","title":"An Empirical Study on Information Extraction using Large Language Models","created":"2023-05-23","cited_by_count":46},{"id":"2302.04335","title":"Will ChatGPT get you caught? Rethinking of Plagiarism Detection","created":"2023-02-08","cited_by_count":41},{"id":"2212.08153","title":"FiDO: Fusion-in-Decoder optimized for stronger performance and faster inference","created":"2022-12-15","cited_by_count":31},{"id":"1906.00500","title":"A Survey of Natural Language Generation Techniques with a Focus on Dialogue Systems - Past, Present and Future Directions","created":"2019-06-02","cited_by_count":26},{"id":"2201.06657","title":"A Literature Survey of Recent Advances in Chatbots","created":"2022-01-17","cited_by_count":26},{"id":"1808.07374","title":"Learning When to Concentrate or Divert Attention: Self-Adaptive Attention Temperature for Neural Machine Translation","created":"2018-08-22","cited_by_count":10},{"id":"2012.02640","title":"A Comparison of Natural Language Understanding Platforms for Chatbots in Software Engineering","created":"2020-12-04","cited_by_count":10},{"id":"2305.18582","title":"Information Association for Language Model Updating by Mitigating LM-Logical Discrepancy","created":"2023-05-29","cited_by_count":10},{"id":"2306.08122","title":"Beyond Black Box AI-Generated Plagiarism Detection: From Sentence to Document Level","created":"2023-06-13","cited_by_count":10},{"id":"2105.11321","title":"Neural Language Models for Nineteenth-Century English","created":"2021-05-24","cited_by_count":7},{"id":"2211.11678","title":"Measuring Harmful Representations in Scandinavian Language Models","created":"2022-11-21","cited_by_count":7},{"id":"1707.08696","title":"Digital Forensic Approaches for Amazon Alexa Ecosystem","created":"2017-07-27","cited_by_count":3}],"next_cursor":null}