{"list":"other","total":76,"rows":[{"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":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1803.05355","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","created":"2018-03-14","cited_by_count":1375},{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743},{"id":"1808.07042","title":"CoQA: A Conversational Question Answering Challenge","created":"2018-08-21","cited_by_count":683},{"id":"1705.04146","title":"Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems","created":"2017-05-11","cited_by_count":650},{"id":"2004.14974","title":"Fact or Fiction: Verifying Scientific Claims","created":"2020-04-30","cited_by_count":554},{"id":"1911.03429","title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","created":"2019-11-08","cited_by_count":530},{"id":"1602.01585","title":"Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering","created":"2016-02-04","cited_by_count":520},{"id":"1812.01193","title":"e-SNLI: Natural Language Inference with Natural Language Explanations","created":"2018-12-04","cited_by_count":468},{"id":"2112.07899","title":"Large Dual Encoders Are Generalizable Retrievers","created":"2021-12-15","cited_by_count":456},{"id":"2012.10289","title":"HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection","created":"2020-12-18","cited_by_count":407},{"id":"2006.14779","title":"Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance","created":"2020-06-26","cited_by_count":399},{"id":"1911.03891","title":"Social Bias Frames: Reasoning about Social and Power Implications of Language","created":"2019-11-10","cited_by_count":380},{"id":"2003.06713","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","created":"2020-03-14","cited_by_count":376},{"id":"1906.02361","title":"Explain Yourself! Leveraging Language Models for Commonsense Reasoning","created":"2019-06-06","cited_by_count":367},{"id":"2308.03296","title":"Studying Large Language Model Generalization with Influence Functions","created":"2023-08-07","cited_by_count":326},{"id":"1605.01713","title":"Not Just a Black Box: Learning Important Features Through Propagating Activation Differences","created":"2016-05-05","cited_by_count":297},{"id":"2001.02114","title":"Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making","created":"2020-01-07","cited_by_count":281},{"id":"1910.11473","title":"QASC: A Dataset for Question Answering via Sentence Composition","created":"2019-10-25","cited_by_count":252},{"id":"2002.04326","title":"ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning","created":"2020-02-11","cited_by_count":217},{"id":"2010.09926","title":"Explainable Automated Fact-Checking for Public Health Claims","created":"2020-10-19","cited_by_count":211},{"id":"2010.07487","title":"Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI","created":"2020-10-15","cited_by_count":167},{"id":"1811.07901","title":"On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detection","created":"2018-11-19","cited_by_count":159},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156},{"id":"2110.01799","title":"ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts","created":"2021-10-05","cited_by_count":148},{"id":"1806.03884","title":"Fast Approximate Natural Gradient Descent in a Kronecker-factored Eigenbasis","created":"2018-06-11","cited_by_count":146},{"id":"2001.08298","title":"Proxy Tasks and Subjective Measures Can Be Misleading in Evaluating Explainable AI Systems","created":"2020-01-22","cited_by_count":139},{"id":"2102.12060","title":"Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing","created":"2021-02-24","cited_by_count":126},{"id":"2110.10790","title":"Human-Centered Explainable AI (XAI): From Algorithms to User Experiences","created":"2021-10-20","cited_by_count":123},{"id":"2210.13777","title":"SciFact-Open: Towards open-domain scientific claim verification","created":"2022-10-25","cited_by_count":94},{"id":"2302.02187","title":"Appropriate Reliance on AI Advice: Conceptualization and the Effect of Explanations","created":"2023-02-04","cited_by_count":83},{"id":"2102.01373","title":"An Improved Baseline for Sentence-level Relation Extraction","created":"2021-02-02","cited_by_count":81},{"id":"2105.13562","title":"ILDC for CJPE: Indian Legal Documents Corpus for Court Judgment Prediction and Explanation","created":"2021-05-28","cited_by_count":78},{"id":"2302.13942","title":"Inseq: An Interpretability Toolkit for Sequence Generation Models","created":"2023-02-27","cited_by_count":78},{"id":"2103.13084","title":"Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Cases","created":"2021-03-24","cited_by_count":77},{"id":"1911.01214","title":"A Richly Annotated Corpus for Different Tasks in Automated Fact-Checking","created":"2019-10-29","cited_by_count":74},{"id":"1904.01606","title":"Inferring Which Medical Treatments Work from Reports of Clinical Trials","created":"2019-04-02","cited_by_count":64},{"id":"2101.09824","title":"Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needs","created":"2021-01-24","cited_by_count":64},{"id":"1802.03052","title":"WorldTree: A Corpus of Explanation Graphs for Elementary Science Questions supporting Multi-Hop Inference","created":"2018-02-08","cited_by_count":60},{"id":"1805.03818","title":"Training Classifiers with Natural Language Explanations","created":"2018-05-10","cited_by_count":58},{"id":"2009.06354","title":"QED: A Framework and Dataset for Explanations in Question Answering","created":"2020-09-08","cited_by_count":55},{"id":"1810.09648","title":"What can AI do for me: Evaluating Machine Learning Interpretations in Cooperative Play","created":"2018-10-23","cited_by_count":53},{"id":"2310.12558","title":"Large Language Models Help Humans Verify Truthfulness -- Except When They Are Convincingly Wrong","created":"2023-10-19","cited_by_count":51},{"id":"2104.04725","title":"Fool Me Twice: Entailment from Wikipedia Gamification","created":"2021-04-10","cited_by_count":50},{"id":"2305.07722","title":"In Search of Verifiability: Explanations Rarely Enable Complementary Performance in AI-Advised Decision Making","created":"2023-05-12","cited_by_count":50},{"id":"2010.03274","title":"Learning to Explain: Datasets and Models for Identifying Valid Reasoning Chains in Multihop Question-Answering","created":"2020-10-07","cited_by_count":49},{"id":"1906.00363","title":"Does It Make Sense? And Why? A Pilot Study for Sense Making and Explanation","created":"2019-06-02","cited_by_count":43},{"id":"2005.05763","title":"WinoWhy: A Deep Diagnosis of Essential Commonsense Knowledge for Answering Winograd Schema Challenge","created":"2020-05-12","cited_by_count":43},{"id":"2005.04177","title":"Evidence Inference 2.0: More Data, Better Models","created":"2020-05-08","cited_by_count":40},{"id":"2206.10847","title":"Connecting Algorithmic Research and Usage Contexts: A Perspective of Contextualized Evaluation for Explainable AI","created":"2022-06-22","cited_by_count":40},{"id":"2305.07095","title":"Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-Text Rationales","created":"2023-05-11","cited_by_count":37},{"id":"1904.04792","title":"Quizbowl: The Case for Incremental Question Answering","created":"2019-04-09","cited_by_count":36},{"id":"1910.04601","title":"R4C: A Benchmark for Evaluating RC Systems to Get the Right Answer for the Right Reason","created":"2019-10-10","cited_by_count":36},{"id":"2004.07493","title":"TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition","created":"2020-04-16","cited_by_count":30},{"id":"2012.08012","title":"Learning to Rationalize for Nonmonotonic Reasoning with Distant Supervision","created":"2020-12-14","cited_by_count":27},{"id":"2112.09669","title":"Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations","created":"2021-12-17","cited_by_count":26},{"id":"2109.02738","title":"Does BERT Learn as Humans Perceive? Understanding Linguistic Styles through Lexica","created":"2021-09-06","cited_by_count":23},{"id":"2005.00806","title":"Teaching Machine Comprehension with Compositional Explanations","created":"2020-05-02","cited_by_count":22},{"id":"2311.01007","title":"Effective Human-AI Teams via Learned Natural Language Rules and Onboarding","created":"2023-11-02","cited_by_count":20},{"id":"1911.01352","title":"Learning from Explanations with Neural Execution Tree","created":"2019-11-04","cited_by_count":18},{"id":"2303.16974","title":"BEVERS: A General, Simple, and Performant Framework for Automatic Fact Verification","created":"2023-03-29","cited_by_count":11},{"id":"2104.08219","title":"Flexible Instance-Specific Rationalization of NLP Models","created":"2021-04-16","cited_by_count":10},{"id":"1809.01499","title":"Extractive Adversarial Networks: High-Recall Explanations for Identifying Personal Attacks in Social Media Posts","created":"2018-09-01","cited_by_count":9},{"id":"2204.07693","title":"Calibrating Trust of Multi-Hop Question Answering Systems with Decompositional Probes","created":"2022-04-16","cited_by_count":9},{"id":"1911.00523","title":"What Gets Echoed? Understanding the \"Pointers\" in Explanations of Persuasive Arguments","created":"2019-11-01","cited_by_count":8},{"id":"2201.06777","title":"COPA-SSE: Semi-structured Explanations for Commonsense Reasoning","created":"2022-01-18","cited_by_count":8}],"next_cursor":null}