{"list":"other","total":79,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"1704.02685","title":"Learning Important Features Through Propagating Activation Differences","created":"2017-04-10","cited_by_count":1458},{"id":"1607.06520","title":"Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings","created":"2016-07-21","cited_by_count":1312},{"id":"2005.14050","title":"Language (Technology) is Power: A Critical Survey of \"Bias\" in NLP","created":"2020-05-28","cited_by_count":956},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"1608.07187","title":"Semantics derived automatically from language corpora contain human-like biases","created":"2016-08-25","cited_by_count":901},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"1703.04009","title":"Automated Hate Speech Detection and the Problem of Offensive Language","created":"2017-03-11","cited_by_count":736},{"id":"1804.06876","title":"Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods","created":"2018-04-18","cited_by_count":659},{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639},{"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":"1909.01326","title":"The Woman Worked as a Babysitter: On Biases in Language Generation","created":"2019-09-03","cited_by_count":541},{"id":"1911.03429","title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","created":"2019-11-08","cited_by_count":530},{"id":"1911.02508","title":"Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods","created":"2019-11-06","cited_by_count":443},{"id":"2012.10289","title":"HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection","created":"2020-12-18","cited_by_count":407},{"id":"1903.04561","title":"Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification","created":"2019-03-11","cited_by_count":404},{"id":"1903.10561","title":"On Measuring Social Biases in Sentence Encoders","created":"2019-03-25","cited_by_count":398},{"id":"1612.08220","title":"Understanding Neural Networks through Representation Erasure","created":"2016-12-24","cited_by_count":224},{"id":"2010.06032","title":"Measuring and Reducing Gendered Correlations in Pre-trained Models","created":"2020-10-12","cited_by_count":224},{"id":"2105.04054","title":"Societal Biases in Language Generation: Progress and Challenges","created":"2021-05-10","cited_by_count":202},{"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":"1808.07231","title":"Reducing Gender Bias in Abusive Language Detection","created":"2018-08-22","cited_by_count":152},{"id":"1809.10610","title":"Counterfactual Fairness in Text Classification through Robustness","created":"2018-09-27","cited_by_count":151},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130},{"id":"1909.07913","title":"Learning to Deceive with Attention-Based Explanations","created":"2019-09-17","cited_by_count":111},{"id":"2401.07927","title":"Are self-explanations from Large Language Models faithful?","created":"2024-01-15","cited_by_count":101},{"id":"2409.00729","title":"ContextCite: Attributing Model Generation to Context","created":"2024-09-01","cited_by_count":98},{"id":"2202.10419","title":"Interpreting Language Models with Contrastive Explanations","created":"2022-02-21","cited_by_count":92},{"id":"2005.02439","title":"Contextualizing Hate Speech Classifiers with Post-hoc Explanation","created":"2020-05-05","cited_by_count":84},{"id":"1910.04210","title":"Perturbation Sensitivity Analysis to Detect Unintended Model Biases","created":"2019-10-09","cited_by_count":74},{"id":"1902.00006","title":"An Evaluation of the Human-Interpretability of Explanation","created":"2019-01-31","cited_by_count":71},{"id":"2203.04212","title":"Measuring the Mixing of Contextual Information in the Transformer","created":"2022-03-08","cited_by_count":65},{"id":"2203.09192","title":"Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists","created":"2022-03-17","cited_by_count":55},{"id":"1611.07270","title":"Investigating the influence of noise and distractors on the interpretation of neural networks","created":"2016-11-22","cited_by_count":54},{"id":"2104.15135","title":"Explanation-Based Human Debugging of NLP Models: A Survey","created":"2021-04-30","cited_by_count":53},{"id":"2305.15853","title":"Sequential Integrated Gradients: a simple but effective method for explaining language models","created":"2023-05-25","cited_by_count":52},{"id":"2310.12860","title":"Probing LLMs for hate speech detection: strengths and vulnerabilities","created":"2023-10-19","cited_by_count":52},{"id":"2405.10431","title":"Thinking Fair and Slow: On the Efficacy of Structured Prompts for Debiasing Language Models","created":"2024-05-16","cited_by_count":45},{"id":"2205.03286","title":"GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers","created":"2022-05-06","cited_by_count":44},{"id":"2107.00323","title":"Combining Feature and Instance Attribution to Detect Artifacts","created":"2021-07-01","cited_by_count":38},{"id":"2309.09825","title":"Bias of AI-Generated Content: An Examination of News Produced by Large Language Models","created":"2023-09-18","cited_by_count":38},{"id":"2301.08110","title":"AtMan: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation","created":"2023-01-19","cited_by_count":31},{"id":"2306.02873","title":"DecompX: Explaining Transformers Decisions by Propagating Token Decomposition","created":"2023-06-05","cited_by_count":31},{"id":"1904.11829","title":"Evaluating Recurrent Neural Network Explanations","created":"2019-04-26","cited_by_count":29},{"id":"2212.10678","title":"Causally Testing Gender Bias in LLMs: A Case Study on Occupational Bias","created":"2022-12-20","cited_by_count":28},{"id":"2204.02947","title":"Marrying Fairness and Explainability in Supervised Learning","created":"2022-04-06","cited_by_count":23},{"id":"2311.02805","title":"Tailoring Self-Rationalizers with Multi-Reward Distillation","created":"2023-11-06","cited_by_count":21},{"id":"2206.03945","title":"Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models","created":"2022-06-08","cited_by_count":20},{"id":"2312.01279","title":"TextGenSHAP: Scalable Post-hoc Explanations in Text Generation with Long Documents","created":"2023-12-03","cited_by_count":17},{"id":"2303.11932","title":"Studying How to Efficiently and Effectively Guide Models with Explanations","created":"2023-03-21","cited_by_count":16},{"id":"2310.13007","title":"A Critical Survey on Fairness Benefits of Explainable AI","created":"2023-10-15","cited_by_count":16},{"id":"2403.12403","title":"Towards Interpretable Hate Speech Detection using Large Language Model-extracted Rationales","created":"2024-03-19","cited_by_count":16},{"id":"2308.12539","title":"CALM : A Multi-task Benchmark for Comprehensive Assessment of Language Model Bias","created":"2023-08-24","cited_by_count":14},{"id":"2404.12545","title":"Latent Concept-based Explanation of NLP Models","created":"2024-04-18","cited_by_count":13},{"id":"2405.18217","title":"Understanding Inter-Concept Relationships in Concept-Based Models","created":"2024-05-28","cited_by_count":13},{"id":"2210.11762","title":"Detecting Unintended Social Bias in Toxic Language Datasets","created":"2022-10-21","cited_by_count":12},{"id":"2006.10531","title":"LimeOut: An Ensemble Approach To Improve Process Fairness","created":"2020-06-17","cited_by_count":11},{"id":"2410.19109","title":"RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework","created":"2024-10-24","cited_by_count":11},{"id":"2003.05330","title":"Fairness by Explicability and Adversarial SHAP Learning","created":"2020-03-11","cited_by_count":9},{"id":"2409.07123","title":"Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandem","created":"2024-09-11","cited_by_count":9},{"id":"2211.00243","title":"Why Is It Hate Speech? Masked Rationale Prediction for Explainable Hate Speech Detection","created":"2022-11-01","cited_by_count":7},{"id":"2109.03756","title":"Diagnostics-Guided Explanation Generation","created":"2021-09-08","cited_by_count":6},{"id":"2406.02625","title":"Progressive Inference: Explaining Decoder-Only Sequence Classification Models Using Intermediate Predictions","created":"2024-06-03","cited_by_count":6},{"id":"2406.10130","title":"The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Pre-trained Language Models","created":"2024-06-14","cited_by_count":6},{"id":"2010.12779","title":"Fair Hate Speech Detection through Evaluation of Social Group Counterfactuals","created":"2020-10-24","cited_by_count":4},{"id":"2211.17046","title":"Rationale-Guided Few-Shot Classification to Detect Abusive Language","created":"2022-11-30","cited_by_count":4},{"id":"2502.12992","title":"B-cos LM: Efficiently Transforming Pre-trained Language Models for Improved Explainability","created":"2025-02-18","cited_by_count":4},{"id":"2503.09219","title":"Rethinking Prompt-based Debiasing in Large Language Models","created":"2025-03-12","cited_by_count":4},{"id":"2412.15628","title":"Can Input Attributions Explain Inductive Reasoning in In-Context Learning?","created":"2024-12-20","cited_by_count":2},{"id":"2502.04863","title":"Enhancing Disinformation Detection with Explainable AI and Named Entity Replacement","created":"2025-02-07","cited_by_count":1}],"next_cursor":null}