{"list":"other","total":60,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"1704.02685","title":"Learning Important Features Through Propagating Activation Differences","created":"2017-04-10","cited_by_count":1458},{"id":"1810.03292","title":"Sanity Checks for Saliency Maps","created":"2018-10-08","cited_by_count":1156},{"id":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"1906.04341","title":"What Does BERT Look At? An Analysis of BERT's Attention","created":"2019-06-11","cited_by_count":1003},{"id":"2004.09297","title":"MPNet: Masked and Permuted Pre-training for Language Understanding","created":"2020-04-20","cited_by_count":981},{"id":"1802.01933","title":"A Survey Of Methods For Explaining Black Box Models","created":"2018-02-06","cited_by_count":973},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"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":"1706.03461","title":"Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learning","created":"2017-06-12","cited_by_count":478},{"id":"1805.01070","title":"What you can cram into a single vector: Probing sentence embeddings for linguistic properties","created":"2018-05-03","cited_by_count":457},{"id":"1710.10547","title":"Interpretation of Neural Networks is Fragile","created":"2017-10-29","cited_by_count":444},{"id":"1909.12434","title":"Learning the Difference that Makes a Difference with Counterfactually-Augmented Data","created":"2019-09-26","cited_by_count":439},{"id":"2106.02997","title":"Causal Abstractions of Neural Networks","created":"2021-06-06","cited_by_count":422},{"id":"2012.09740","title":"Understanding the Behaviour of Contrastive Loss","created":"2020-12-15","cited_by_count":398},{"id":"2305.00050","title":"Causal Reasoning and Large Language Models: Opening a New Frontier for Causality","created":"2023-04-28","cited_by_count":353},{"id":"1606.08813","title":"European Union regulations on algorithmic decision-making and a \"right to explanation\"","created":"2016-06-28","cited_by_count":344},{"id":"1906.04571","title":"Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology","created":"2019-06-11","cited_by_count":200},{"id":"1604.00825","title":"Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers","created":"2016-04-04","cited_by_count":199},{"id":"2109.00725","title":"Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond","created":"2021-09-02","cited_by_count":178},{"id":"2010.12762","title":"Measuring Association Between Labels and Free-Text Rationales","created":"2020-10-24","cited_by_count":160},{"id":"1809.10610","title":"Counterfactual Fairness in Text Classification through Robustness","created":"2018-09-27","cited_by_count":151},{"id":"1907.07165","title":"Explaining Classifiers with Causal Concept Effect (CaCE)","created":"2019-07-16","cited_by_count":135},{"id":"2106.06087","title":"Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models","created":"2021-06-10","cited_by_count":131},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130},{"id":"2005.13407","title":"CausaLM: Causal Model Explanation Through Counterfactual Language Models","created":"2020-05-27","cited_by_count":117},{"id":"1705.01359","title":"FOIL it! Find One mismatch between Image and Language caption","created":"2017-05-03","cited_by_count":95},{"id":"2012.00893","title":"Evaluating Explanations: How much do explanations from the teacher aid students?","created":"2020-12-01","cited_by_count":94},{"id":"1705.05598","title":"Learning how to explain neural networks: PatternNet and PatternAttribution","created":"2017-05-16","cited_by_count":84},{"id":"2103.00242","title":"A Survey on Stance Detection for Mis- and Disinformation Identification","created":"2021-02-27","cited_by_count":75},{"id":"2107.07150","title":"Tailor: Generating and Perturbing Text with Semantic Controls","created":"2021-07-15","cited_by_count":68},{"id":"2010.02114","title":"Explaining The Efficacy of Counterfactually Augmented Data","created":"2020-10-05","cited_by_count":65},{"id":"2102.12206","title":"PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domains","created":"2021-02-24","cited_by_count":61},{"id":"2202.00734","title":"Framework for Evaluating Faithfulness of Local Explanations","created":"2022-02-01","cited_by_count":55},{"id":"2205.14140","title":"CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior","created":"2022-05-27","cited_by_count":55},{"id":"2012.12265","title":"Generative Interventions for Causal Learning","created":"2020-12-22","cited_by_count":45},{"id":"2201.12114","title":"Rethinking Attention-Model Explainability through Faithfulness Violation Test","created":"2022-01-28","cited_by_count":43},{"id":"2202.12350","title":"DoCoGen: Domain Counterfactual Generation for Low Resource Domain Adaptation","created":"2022-02-24","cited_by_count":37},{"id":"1910.09113","title":"Discovering the Compositional Structure of Vector Representations with Role Learning Networks","created":"2019-10-21","cited_by_count":34},{"id":"2104.07467","title":"Cross-Domain Label-Adaptive Stance Detection","created":"2021-04-15","cited_by_count":30},{"id":"2104.08782","title":"On the Sensitivity and Stability of Model Interpretations in NLP","created":"2021-04-18","cited_by_count":30},{"id":"2209.14279","title":"Causal Proxy Models for Concept-Based Model Explanations","created":"2022-09-28","cited_by_count":29},{"id":"2305.02031","title":"A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Training","created":"2023-05-03","cited_by_count":16},{"id":"1807.01395","title":"Patient representation learning and interpretable evaluation using clinical notes","created":"2018-07-03","cited_by_count":15},{"id":"2106.04484","title":"Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions","created":"2021-06-08","cited_by_count":15},{"id":"2005.01672","title":"Evaluating Explanation Methods for Neural Machine Translation","created":"2020-05-04","cited_by_count":14},{"id":"2205.12469","title":"Logical Satisfiability of Counterfactuals for Faithful Explanations in NLI","created":"2022-05-25","cited_by_count":11},{"id":"2206.05700","title":"A Functional Information Perspective on Model Interpretation","created":"2022-06-12","cited_by_count":5}],"next_cursor":null}