{"list":"other","total":156,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"1808.08745","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","created":"2018-08-27","cited_by_count":1317},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"2004.04696","title":"BLEURT: Learning Robust Metrics for Text Generation","created":"2020-04-09","cited_by_count":1203},{"id":"1810.03993","title":"Model Cards for Model Reporting","created":"2018-10-05","cited_by_count":1080},{"id":"1506.03340","title":"Teaching Machines to Read and Comprehend","created":"2015-06-10","cited_by_count":1049},{"id":"2009.09025","title":"COMET: A Neural Framework for MT Evaluation","created":"2020-09-18","cited_by_count":1033},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"2005.14050","title":"Language (Technology) is Power: A Critical Survey of \"Bias\" in NLP","created":"2020-05-28","cited_by_count":956},{"id":"1809.05053","title":"XNLI: Evaluating Cross-lingual Sentence Representations","created":"2018-09-13","cited_by_count":915},{"id":"2005.00661","title":"On Faithfulness and Factuality in Abstractive Summarization","created":"2020-05-02","cited_by_count":900},{"id":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886},{"id":"1902.01007","title":"Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference","created":"2019-02-04","cited_by_count":876},{"id":"1602.06023","title":"Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond","created":"2016-02-19","cited_by_count":812},{"id":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"2004.09095","title":"The State and Fate of Linguistic Diversity and Inclusion in the NLP World","created":"2020-04-20","cited_by_count":798},{"id":"1810.00278","title":"MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling","created":"2018-09-29","cited_by_count":766},{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"id":"2007.12626","title":"SummEval: Re-evaluating Summarization Evaluation","created":"2020-07-24","cited_by_count":674},{"id":"1910.12840","title":"Evaluating the Factual Consistency of Abstractive Text Summarization","created":"2019-10-28","cited_by_count":584},{"id":"1905.12616","title":"Defending Against Neural Fake News","created":"2019-05-29","cited_by_count":559},{"id":"1911.12237","title":"SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization","created":"2019-11-27","cited_by_count":535},{"id":"2109.02846","title":"Datasets: A Community Library for Natural Language Processing","created":"2021-09-07","cited_by_count":530},{"id":"1906.04043","title":"GLTR: Statistical Detection and Visualization of Generated Text","created":"2019-06-10","cited_by_count":496},{"id":"2104.08758","title":"Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus","created":"2021-04-18","cited_by_count":492},{"id":"2102.01454","title":"MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers","created":"2021-02-02","cited_by_count":470},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"1909.02622","title":"MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance","created":"2019-09-05","cited_by_count":418},{"id":"1509.00685","title":"A Neural Attention Model for Abstractive Sentence Summarization","created":"2015-09-02","cited_by_count":396},{"id":"2004.04228","title":"Asking and Answering Questions to Evaluate the Factual Consistency of Summaries","created":"2020-04-08","cited_by_count":378},{"id":"1705.04304","title":"A Deep Reinforced Model for Abstractive Summarization","created":"2017-05-11","cited_by_count":365},{"id":"2106.13822","title":"XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages","created":"2021-06-25","cited_by_count":347},{"id":"2104.14478","title":"Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translation","created":"2021-04-29","cited_by_count":338},{"id":"1804.11283","title":"Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies","created":"2018-04-30","cited_by_count":294},{"id":"2005.03754","title":"FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization","created":"2020-05-07","cited_by_count":293},{"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":"2107.00061","title":"All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text","created":"2021-06-30","cited_by_count":287},{"id":"1812.08951","title":"Analysis Methods in Neural Language Processing: A Survey","created":"2018-12-21","cited_by_count":277},{"id":"2006.14799","title":"Evaluation of Text Generation: A Survey","created":"2020-06-26","cited_by_count":277},{"id":"2004.14373","title":"ToTTo: A Controlled Table-To-Text Generation Dataset","created":"2020-04-29","cited_by_count":268},{"id":"1911.00650","title":"Automatic Detection of Generated Text is Easiest when Humans are Fooled","created":"2019-11-02","cited_by_count":261},{"id":"2012.05345","title":"Data and its (dis)contents: A survey of dataset development and use in machine learning research","created":"2020-12-09","cited_by_count":260},{"id":"2112.12870","title":"Measuring Attribution in Natural Language Generation Models","created":"2021-12-23","cited_by_count":256},{"id":"1706.09254","title":"The E2E Dataset: New Challenges For End-to-End Generation","created":"2017-06-28","cited_by_count":253},{"id":"1611.04230","title":"SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents","created":"2016-11-14","cited_by_count":246},{"id":"2103.12693","title":"QuestEval: Summarization Asks for Fact-based Evaluation","created":"2021-03-23","cited_by_count":244},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239},{"id":"2112.08542","title":"QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization","created":"2021-12-16","cited_by_count":236},{"id":"1707.06875","title":"Why We Need New Evaluation Metrics for NLG","created":"2017-07-21","cited_by_count":233},{"id":"1707.08052","title":"Challenges in Data-to-Document Generation","created":"2017-07-25","cited_by_count":226},{"id":"1703.09902","title":"Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation","created":"2017-03-29","cited_by_count":206},{"id":"2104.02145","title":"What Will it Take to Fix Benchmarking in Natural Language Understanding?","created":"2021-04-05","cited_by_count":203},{"id":"1608.08868","title":"Demographic Dialectal Variation in Social Media: A Case Study of African-American English","created":"2016-08-31","cited_by_count":196},{"id":"1908.08960","title":"Neural Text Summarization: A Critical Evaluation","created":"2019-08-23","cited_by_count":189},{"id":"1808.10792","title":"Bottom-Up Abstractive Summarization","created":"2018-08-31","cited_by_count":177},{"id":"1909.03004","title":"Show Your Work: Improved Reporting of Experimental Results","created":"2019-09-06","cited_by_count":169},{"id":"2107.10821","title":"To Ship or Not to Ship: An Extensive Evaluation of Automatic Metrics for Machine Translation","created":"2021-07-22","cited_by_count":163},{"id":"2010.03093","title":"WikiLingua: A New Benchmark Dataset for Cross-Lingual Abstractive Summarization","created":"2020-10-07","cited_by_count":154},{"id":"2010.07100","title":"Re-evaluating Evaluation in Text Summarization","created":"2020-10-14","cited_by_count":145},{"id":"2010.06595","title":"With Little Power Comes Great Responsibility","created":"2020-10-13","cited_by_count":142},{"id":"2010.13561","title":"Towards Accountability for Machine Learning Datasets: Practices from Software Engineering and Infrastructure","created":"2020-10-23","cited_by_count":138},{"id":"1905.13164","title":"Hierarchical Transformers for Multi-Document Summarization","created":"2019-05-30","cited_by_count":132},{"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":"2104.04302","title":"Annotating and Modeling Fine-grained Factuality in Summarization","created":"2021-04-09","cited_by_count":131},{"id":"1904.02792","title":"Unifying Human and Statistical Evaluation for Natural Language Generation","created":"2019-04-04","cited_by_count":127},{"id":"2110.05699","title":"On Releasing Annotator-Level Labels and Information in Datasets","created":"2021-10-12","cited_by_count":126},{"id":"2008.05122","title":"The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models","created":"2020-08-12","cited_by_count":125},{"id":"2112.08674","title":"Reframing Human-AI Collaboration for Generating Free-Text Explanations","created":"2021-12-16","cited_by_count":125},{"id":"2004.14900","title":"MLSUM: The Multilingual Summarization Corpus","created":"2020-04-30","cited_by_count":121},{"id":"1906.01081","title":"Handling Divergent Reference Texts when Evaluating Table-to-Text Generation","created":"2019-06-03","cited_by_count":119},{"id":"2004.14564","title":"Automatic Machine Translation Evaluation in Many Languages via Zero-Shot Paraphrasing","created":"2020-04-30","cited_by_count":115},{"id":"2004.06063","title":"BLEU might be Guilty but References are not Innocent","created":"2020-04-13","cited_by_count":110},{"id":"2010.08712","title":"Factual Error Correction for Abstractive Summarization Models","created":"2020-10-17","cited_by_count":108},{"id":"2101.04840","title":"Robustness Gym: Unifying the NLP Evaluation Landscape","created":"2021-01-13","cited_by_count":108},{"id":"1809.00582","title":"Data-to-Text Generation with Content Selection and Planning","created":"2018-09-03","cited_by_count":106},{"id":"2112.01716","title":"Reduced, Reused and Recycled: The Life of a Dataset in Machine Learning Research","created":"2021-12-03","cited_by_count":102},{"id":"2109.06835","title":"The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation","created":"2021-09-14","cited_by_count":97},{"id":"2110.06341","title":"Learning Compact Metrics for MT","created":"2021-10-12","cited_by_count":93},{"id":"1909.01610","title":"Answers Unite! Unsupervised Metrics for Reinforced Summarization Models","created":"2019-09-04","cited_by_count":92},{"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":"2108.12237","title":"Evaluating the Robustness of Neural Language Models to Input Perturbations","created":"2021-08-27","cited_by_count":87},{"id":"1901.07931","title":"Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge","created":"2019-01-23","cited_by_count":86},{"id":"2108.04308","title":"Do Datasets Have Politics? Disciplinary Values in Computer Vision Dataset Development","created":"2021-08-09","cited_by_count":85},{"id":"1909.06694","title":"Beyond BLEU: Training Neural Machine Translation with Semantic Similarity","created":"2019-09-14","cited_by_count":84},{"id":"1907.01752","title":"On the Weaknesses of Reinforcement Learning for Neural Machine Translation","created":"2019-07-03","cited_by_count":82},{"id":"2104.06486","title":"MS2: Multi-Document Summarization of Medical Studies","created":"2021-04-13","cited_by_count":80},{"id":"2105.02732","title":"What's in the Box? A Preliminary Analysis of Undesirable Content in the Common Crawl Corpus","created":"2021-05-06","cited_by_count":80},{"id":"1712.01765","title":"Best-Worst Scaling More Reliable than Rating Scales: A Case Study on Sentiment Intensity Annotation","created":"2017-12-05","cited_by_count":79},{"id":"2107.03451","title":"Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling","created":"2021-07-07","cited_by_count":78},{"id":"2010.12834","title":"GO FIGURE: A Meta Evaluation of Factuality in Summarization","created":"2020-10-24","cited_by_count":76},{"id":"2104.07606","title":"Planning with Learned Entity Prompts for Abstractive Summarization","created":"2021-04-15","cited_by_count":75}],"next_cursor":"100"}