{"list":"other","total":52,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276},{"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":"1803.05355","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","created":"2018-03-14","cited_by_count":1375},{"id":"2212.10511","title":"When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories","created":"2022-12-20","cited_by_count":1128},{"id":"2204.07705","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","created":"2022-04-16","cited_by_count":868},{"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":"1704.00051","title":"Reading Wikipedia to Answer Open-Domain Questions","created":"2017-03-31","cited_by_count":777},{"id":"2104.07567","title":"Retrieval Augmentation Reduces Hallucination in Conversation","created":"2021-04-15","cited_by_count":692},{"id":"2303.13375","title":"Capabilities of GPT-4 on Medical Challenge Problems","created":"2023-03-20","cited_by_count":638},{"id":"1910.12840","title":"Evaluating the Factual Consistency of Abstractive Text Summarization","created":"2019-10-28","cited_by_count":584},{"id":"2009.02252","title":"KILT: a Benchmark for Knowledge Intensive Language Tasks","created":"2020-09-04","cited_by_count":573},{"id":"2004.14974","title":"Fact or Fiction: Verifying Scientific Claims","created":"2020-04-30","cited_by_count":554},{"id":"2301.07597","title":"How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection","created":"2023-01-18","cited_by_count":481},{"id":"2211.08411","title":"Large Language Models Struggle to Learn Long-Tail Knowledge","created":"2022-11-15","cited_by_count":458},{"id":"2112.07899","title":"Large Dual Encoders Are Generalizable Retrievers","created":"2021-12-15","cited_by_count":456},{"id":"2111.09525","title":"SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization","created":"2021-11-18","cited_by_count":407},{"id":"2004.04228","title":"Asking and Answering Questions to Evaluate the Factual Consistency of Summaries","created":"2020-04-08","cited_by_count":378},{"id":"2304.09848","title":"Evaluating Verifiability in Generative Search Engines","created":"2023-04-19","cited_by_count":303},{"id":"2104.13346","title":"Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics","created":"2021-04-27","cited_by_count":287},{"id":"2112.12870","title":"Measuring Attribution in Natural Language Generation Models","created":"2021-12-23","cited_by_count":256},{"id":"2112.08542","title":"QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization","created":"2021-12-16","cited_by_count":236},{"id":"2212.10450","title":"Is GPT-3 a Good Data Annotator?","created":"2022-12-20","cited_by_count":208},{"id":"2206.04624","title":"Factuality Enhanced Language Models for Open-Ended Text Generation","created":"2022-06-09","cited_by_count":202},{"id":"2010.07100","title":"Re-evaluating Evaluation in Text Summarization","created":"2020-10-14","cited_by_count":145},{"id":"2212.07981","title":"Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation","created":"2022-12-15","cited_by_count":142},{"id":"2303.01432","title":"WiCE: Real-World Entailment for Claims in Wikipedia","created":"2023-03-02","cited_by_count":120},{"id":"2004.14564","title":"Automatic Machine Translation Evaluation in Many Languages via Zero-Shot Paraphrasing","created":"2020-04-30","cited_by_count":115},{"id":"2212.08037","title":"Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models","created":"2022-12-15","cited_by_count":112},{"id":"2301.13298","title":"LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization","created":"2023-01-30","cited_by_count":96},{"id":"2210.13777","title":"SciFact-Open: Towards open-domain scientific claim verification","created":"2022-10-25","cited_by_count":94},{"id":"1709.08878","title":"Generating Sentences by Editing Prototypes","created":"2017-09-26","cited_by_count":88},{"id":"2010.00490","title":"Towards Question-Answering as an Automatic Metric for Evaluating the Content Quality of a Summary","created":"2020-10-01","cited_by_count":88},{"id":"1906.03538","title":"Seeing Things from a Different Angle: Discovering Diverse Perspectives about Claims","created":"2019-06-08","cited_by_count":74},{"id":"2305.06311","title":"Automatic Evaluation of Attribution by Large Language Models","created":"2023-05-10","cited_by_count":72},{"id":"2205.06938","title":"Generating Literal and Implied Subquestions to Fact-check Complex Claims","created":"2022-05-14","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":"2011.05448","title":"Generating Fact Checking Briefs","created":"2020-11-10","cited_by_count":50},{"id":"2109.11503","title":"Finding a Balanced Degree of Automation for Summary Evaluation","created":"2021-09-23","cited_by_count":43},{"id":"1808.05542","title":"Overview of the CLEF-2018 CheckThat! Lab on Automatic Identification and Verification of Political Claims. Task 1: Check-Worthiness","created":"2018-08-08","cited_by_count":41},{"id":"2212.01349","title":"Nonparametric Masked Language Modeling","created":"2022-12-02","cited_by_count":40},{"id":"1904.05929","title":"Crowdsourcing Lightweight Pyramids for Manual Summary Evaluation","created":"2019-04-11","cited_by_count":39},{"id":"2104.15114","title":"Paraphrastic Representations at Scale","created":"2021-04-30","cited_by_count":21},{"id":"1906.01727","title":"SemEval-2019 Task 8: Fact Checking in Community Question Answering Forums","created":"2019-05-25","cited_by_count":18},{"id":"2104.07423","title":"The Role of Context in Detecting Previously Fact-Checked Claims","created":"2021-04-15","cited_by_count":17}],"next_cursor":null}