{"list":"other","total":57,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"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":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"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":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"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":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"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":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751},{"id":"2002.08910","title":"How Much Knowledge Can You Pack Into the Parameters of a Language Model?","created":"2020-02-10","cited_by_count":719},{"id":"2304.13734","title":"The Internal State of an LLM Knows When It's Lying","created":"2023-04-26","cited_by_count":659},{"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":"2004.04228","title":"Asking and Answering Questions to Evaluate the Factual Consistency of Summaries","created":"2020-04-08","cited_by_count":378},{"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":"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":"2311.08298","title":"A Survey of Confidence Estimation and Calibration in Large Language Models","created":"2023-11-14","cited_by_count":256},{"id":"2202.06991","title":"Transformer Memory as a Differentiable Search Index","created":"2022-02-14","cited_by_count":247},{"id":"2103.12693","title":"QuestEval: Summarization Asks for Fact-based Evaluation","created":"2021-03-23","cited_by_count":244},{"id":"2307.12976","title":"Evaluating the Ripple Effects of Knowledge Editing in Language Models","created":"2023-07-24","cited_by_count":242},{"id":"2006.09462","title":"Selective Question Answering under Domain Shift","created":"2020-06-16","cited_by_count":238},{"id":"2004.07213","title":"Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims","created":"2020-04-15","cited_by_count":165},{"id":"2305.13281","title":"LM vs LM: Detecting Factual Errors via Cross Examination","created":"2023-05-22","cited_by_count":156},{"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":"2305.15852","title":"Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation","created":"2023-05-25","cited_by_count":124},{"id":"2212.08037","title":"Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models","created":"2022-12-15","cited_by_count":112},{"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":"2305.06311","title":"Automatic Evaluation of Attribution by Large Language Models","created":"2023-05-10","cited_by_count":72},{"id":"2308.06374","title":"Large Language Models and Knowledge Graphs: Opportunities and Challenges","created":"2023-08-11","cited_by_count":71},{"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":"2211.00151","title":"A Close Look into the Calibration of Pre-trained Language Models","created":"2022-10-31","cited_by_count":57},{"id":"2406.04306","title":"Improving Uncertainty Estimation through Semantically Diverse Language Generation","created":"2024-06-06","cited_by_count":35},{"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":"2403.00025","title":"On the Challenges and Opportunities in Generative AI","created":"2024-02-28","cited_by_count":31},{"id":"1906.00424","title":"Plain English Summarization of Contracts","created":"2019-06-02","cited_by_count":28},{"id":"2301.09201","title":"SPEC5G: A Dataset for 5G Cellular Network Protocol Analysis","created":"2023-01-22","cited_by_count":20},{"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}