{"list":"other","total":59,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"id":"2210.03350","title":"Measuring and Narrowing the Compositionality Gap in Language Models","created":"2022-10-07","cited_by_count":1075},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"2005.00661","title":"On Faithfulness and Factuality in Abstractive Summarization","created":"2020-05-02","cited_by_count":900},{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819},{"id":"1911.00172","title":"Generalization through Memorization: Nearest Neighbor Language Models","created":"2019-11-01","cited_by_count":800},{"id":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751},{"id":"2012.00955","title":"How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering","created":"2020-12-02","cited_by_count":445},{"id":"1805.00899","title":"AI safety via debate","created":"2018-05-02","cited_by_count":400},{"id":"2004.04228","title":"Asking and Answering Questions to Evaluate the Factual Consistency of Summaries","created":"2020-04-08","cited_by_count":378},{"id":"2104.06599","title":"Learning How to Ask: Querying LMs with Mixtures of Soft Prompts","created":"2021-04-14","cited_by_count":377},{"id":"2102.01017","title":"Measuring and Improving Consistency in Pretrained Language Models","created":"2021-02-01","cited_by_count":364},{"id":"2003.07892","title":"Calibration of Pre-trained Transformers","created":"2020-03-17","cited_by_count":315},{"id":"2304.09848","title":"Evaluating Verifiability in Generative Search Engines","created":"2023-04-19","cited_by_count":303},{"id":"2208.04024","title":"Social Simulacra: Creating Populated Prototypes for Social Computing Systems","created":"2022-08-08","cited_by_count":301},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292},{"id":"2104.05240","title":"Factual Probing Is [MASK]: Learning vs. Learning to Recall","created":"2021-04-12","cited_by_count":291},{"id":"2210.08726","title":"RARR: Researching and Revising What Language Models Say, Using Language Models","created":"2022-10-17","cited_by_count":287},{"id":"2112.12870","title":"Measuring Attribution in Natural Language Generation Models","created":"2021-12-23","cited_by_count":256},{"id":"2103.12693","title":"QuestEval: Summarization Asks for Fact-based Evaluation","created":"2021-03-23","cited_by_count":244},{"id":"2006.09462","title":"Selective Question Answering under Domain Shift","created":"2020-06-16","cited_by_count":238},{"id":"2305.08291","title":"Large Language Model Guided Tree-of-Thought","created":"2023-05-15","cited_by_count":221},{"id":"2302.07459","title":"The Capacity for Moral Self-Correction in Large Language Models","created":"2023-02-15","cited_by_count":173},{"id":"2004.07213","title":"Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims","created":"2020-04-15","cited_by_count":165},{"id":"2205.11822","title":"Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations","created":"2022-05-24","cited_by_count":159},{"id":"1811.00671","title":"Dialogue Natural Language Inference","created":"2018-11-01","cited_by_count":135},{"id":"2104.08202","title":"$Q^{2}$: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering","created":"2021-04-16","cited_by_count":132},{"id":"2205.12674","title":"Training Language Models with Memory Augmentation","created":"2022-05-25","cited_by_count":113},{"id":"1811.10971","title":"The Fact Extraction and VERification (FEVER) Shared Task","created":"2018-11-27","cited_by_count":108},{"id":"2211.08412","title":"Evaluating the Factual Consistency of Large Language Models Through News Summarization","created":"2022-11-15","cited_by_count":92},{"id":"2304.13007","title":"Answering Questions by Meta-Reasoning over Multiple Chains of Thought","created":"2023-04-25","cited_by_count":87},{"id":"2208.11663","title":"PEER: A Collaborative Language Model","created":"2022-08-24","cited_by_count":86},{"id":"2301.12810","title":"Crawling the Internal Knowledge-Base of Language Models","created":"2023-01-30","cited_by_count":85},{"id":"2305.11171","title":"TrueTeacher: Learning Factual Consistency Evaluation with Large Language Models","created":"2023-05-18","cited_by_count":83},{"id":"2105.00071","title":"Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark","created":"2021-04-30","cited_by_count":77},{"id":"2205.00049","title":"Prompt Consistency for Zero-Shot Task Generalization","created":"2022-04-29","cited_by_count":67},{"id":"2203.00211","title":"Investigating Selective Prediction Approaches Across Several Tasks in IID, OOD, and Adversarial Settings","created":"2022-03-01","cited_by_count":66},{"id":"2203.12990","title":"Generating Scientific Claims for Zero-Shot Scientific Fact Checking","created":"2022-03-24","cited_by_count":59},{"id":"2204.07562","title":"Evaluating Factuality in Text Simplification","created":"2022-04-15","cited_by_count":34},{"id":"2208.11057","title":"Prompting as Probing: Using Language Models for Knowledge Base Construction","created":"2022-08-23","cited_by_count":32},{"id":"2304.08653","title":"On Uncertainty Calibration and Selective Generation in Probabilistic Neural Summarization: A Benchmark Study","created":"2023-04-17","cited_by_count":25},{"id":"2110.07280","title":"P-Adapters: Robustly Extracting Factual Information from Language Models with Diverse Prompts","created":"2021-10-14","cited_by_count":22},{"id":"2210.06748","title":"Shortcomings of Question Answering Based Factuality Frameworks for Error Localization","created":"2022-10-13","cited_by_count":15},{"id":"2204.02007","title":"Fact Checking with Insufficient Evidence","created":"2022-04-05","cited_by_count":11}],"next_cursor":null}