{"list":"other","total":51,"rows":[{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1706.07269","title":"Explanation in Artificial Intelligence: Insights from the Social Sciences","created":"2017-06-22","cited_by_count":1206},{"id":"2004.04696","title":"BLEURT: Learning Robust Metrics for Text Generation","created":"2020-04-09","cited_by_count":1203},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"2004.03685","title":"Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?","created":"2020-04-07","cited_by_count":599},{"id":"1911.03429","title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","created":"2019-11-08","cited_by_count":530},{"id":"1812.01193","title":"e-SNLI: Natural Language Inference with Natural Language Explanations","created":"2018-12-04","cited_by_count":468},{"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":"1603.08023","title":"How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation","created":"2016-03-25","cited_by_count":356},{"id":"1904.07451","title":"Counterfactual Visual Explanations","created":"2019-04-16","cited_by_count":313},{"id":"2201.08164","title":"From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI","created":"2022-01-20","cited_by_count":302},{"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":"1707.06875","title":"Why We Need New Evaluation Metrics for NLG","created":"2017-07-21","cited_by_count":233},{"id":"2110.08387","title":"Generated Knowledge Prompting for Commonsense Reasoning","created":"2021-10-15","cited_by_count":214},{"id":"2005.01831","title":"Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?","created":"2020-05-04","cited_by_count":190},{"id":"2009.13295","title":"A Diagnostic Study of Explainability Techniques for Text Classification","created":"2020-09-25","cited_by_count":159},{"id":"1803.04585","title":"Categorizing Variants of Goodhart's Law","created":"2018-03-13","cited_by_count":149},{"id":"2004.14546","title":"WT5?! Training Text-to-Text Models to Explain their Predictions","created":"2020-04-30","cited_by_count":148},{"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":"1906.02916","title":"Multi-hop Reading Comprehension through Question Decomposition and Rescoring","created":"2019-06-07","cited_by_count":119},{"id":"2112.04417","title":"What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methods","created":"2021-12-06","cited_by_count":98},{"id":"2005.12116","title":"NILE : Natural Language Inference with Faithful Natural Language Explanations","created":"2020-05-25","cited_by_count":96},{"id":"2012.00893","title":"Evaluating Explanations: How much do explanations from the teacher aid students?","created":"2020-12-01","cited_by_count":94},{"id":"2105.03761","title":"e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks","created":"2021-05-08","cited_by_count":84},{"id":"1911.03631","title":"Hierarchical Graph Network for Multi-hop Question Answering","created":"2019-11-09","cited_by_count":83},{"id":"1901.03729","title":"Automated Rationale Generation: A Technique for Explainable AI and its Effects on Human Perceptions","created":"2019-01-11","cited_by_count":81},{"id":"1810.05995","title":"BLEU is Not Suitable for the Evaluation of Text Simplification","created":"2018-10-14","cited_by_count":78},{"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":"1911.00484","title":"Select, Answer and Explain: Interpretable Multi-hop Reading Comprehension over Multiple Documents","created":"2019-11-01","cited_by_count":57},{"id":"2010.02180","title":"Pareto Probing: Trading Off Accuracy for Complexity","created":"2020-10-05","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":"1811.00731","title":"The age of secrecy and unfairness in recidivism prediction","created":"2018-11-02","cited_by_count":53},{"id":"2004.07769","title":"SCOUT: Self-aware Discriminant Counterfactual Explanations","created":"2020-04-16","cited_by_count":52},{"id":"1810.00184","title":"Stakeholders in Explainable AI","created":"2018-09-29","cited_by_count":48},{"id":"2110.07038","title":"Towards Efficient NLP: A Standard Evaluation and A Strong Baseline","created":"2021-10-13","cited_by_count":44},{"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":"2107.00323","title":"Combining Feature and Instance Attribution to Detect Artifacts","created":"2021-07-01","cited_by_count":38},{"id":"2002.08512","title":"The Problem with Metrics is a Fundamental Problem for AI","created":"2020-02-20","cited_by_count":37},{"id":"2007.12248","title":"Are Visual Explanations Useful? A Case Study in Model-in-the-Loop Prediction","created":"2020-07-23","cited_by_count":36},{"id":"2103.08545","title":"A Study of Automatic Metrics for the Evaluation of Natural Language Explanations","created":"2021-03-15","cited_by_count":34},{"id":"2201.11569","title":"Human Interpretation of Saliency-based Explanation Over Text","created":"2022-01-27","cited_by_count":25},{"id":"2201.11239","title":"Diagnosing AI Explanation Methods with Folk Concepts of Behavior","created":"2022-01-27","cited_by_count":15},{"id":"2106.15355","title":"On the Interaction of Belief Bias and Explanations","created":"2021-06-29","cited_by_count":13},{"id":"2205.11729","title":"From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answering","created":"2022-05-24","cited_by_count":12},{"id":"2010.06283","title":"F1 is Not Enough! Models and Evaluation Towards User-Centered Explainable Question Answering","created":"2020-10-13","cited_by_count":11},{"id":"2109.07833","title":"Does External Knowledge Help Explainable Natural Language Inference? Automatic Evaluation vs. Human Ratings","created":"2021-09-16","cited_by_count":9},{"id":"1910.04731","title":"Automatic Quality Estimation for Natural Language Generation: Ranting (Jointly Rating and Ranking)","created":"2019-10-10","cited_by_count":4},{"id":"2111.09029","title":"Towards Interpretable and Reliable Reading Comprehension: A Pipeline Model with Unanswerability Prediction","created":"2021-11-17","cited_by_count":3},{"id":"2205.02005","title":"A Framework to Generate High-Quality Datapoints for Multiple Novel Intent Detection","created":"2022-05-04","cited_by_count":2},{"id":"2002.02526","title":"How to Answer Why -- Evaluating the Explanations of AI Through Mental Model Analysis","created":"2020-01-11","cited_by_count":1}],"next_cursor":null}