{"list":"other","total":134,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"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":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"1910.10045","title":"Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI","created":"2019-10-22","cited_by_count":1552},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"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":"1706.07269","title":"Explanation in Artificial Intelligence: Insights from the Social Sciences","created":"2017-06-22","cited_by_count":1206},{"id":"1810.03292","title":"Sanity Checks for Saliency Maps","created":"2018-10-08","cited_by_count":1156},{"id":"2305.04388","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","created":"2023-05-07","cited_by_count":1122},{"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":"1608.07187","title":"Semantics derived automatically from language corpora contain human-like biases","created":"2016-08-25","cited_by_count":901},{"id":"2307.13702","title":"Measuring Faithfulness in Chain-of-Thought Reasoning","created":"2023-07-17","cited_by_count":703},{"id":"1909.03368","title":"Designing and Interpreting Probes with Control Tasks","created":"2019-09-08","cited_by_count":640},{"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":"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":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422},{"id":"2012.10289","title":"HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection","created":"2020-12-18","cited_by_count":407},{"id":"1907.07374","title":"A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI","created":"2019-07-17","cited_by_count":404},{"id":"1906.02361","title":"Explain Yourself! Leveraging Language Models for Commonsense Reasoning","created":"2019-06-06","cited_by_count":367},{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367},{"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":"1608.05745","title":"RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism","created":"2016-08-19","cited_by_count":349},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333},{"id":"1906.05714","title":"A Multiscale Visualization of Attention in the Transformer Model","created":"2019-06-12","cited_by_count":292},{"id":"1606.01541","title":"Deep Reinforcement Learning for Dialogue Generation","created":"2016-06-05","cited_by_count":288},{"id":"2301.13379","title":"Faithful Chain-of-Thought Reasoning","created":"2023-01-31","cited_by_count":288},{"id":"1606.04155","title":"Rationalizing Neural Predictions","created":"2016-06-13","cited_by_count":281},{"id":"1812.04608","title":"Metrics for Explainable AI: Challenges and Prospects","created":"2018-12-11","cited_by_count":260},{"id":"1802.07814","title":"Learning to Explain: An Information-Theoretic Perspective on Model Interpretation","created":"2018-02-21","cited_by_count":248},{"id":"1808.00033","title":"Techniques for Interpretable Machine Learning","created":"2018-07-31","cited_by_count":238},{"id":"1806.08730","title":"The Natural Language Decathlon: Multitask Learning as Question Answering","created":"2018-06-20","cited_by_count":236},{"id":"1802.05695","title":"Explainable Prediction of Medical Codes from Clinical Text","created":"2018-02-15","cited_by_count":234},{"id":"1606.05386","title":"Model-Agnostic Interpretability of Machine Learning","created":"2016-06-16","cited_by_count":219},{"id":"2501.17148","title":"AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders","created":"2025-01-28","cited_by_count":218},{"id":"1511.05942","title":"Doctor AI: Predicting Clinical Events via Recurrent Neural Networks","created":"2015-11-18","cited_by_count":208},{"id":"2010.00711","title":"A Survey of the State of Explainable AI for Natural Language Processing","created":"2020-10-01","cited_by_count":206},{"id":"2004.00053","title":"Information Leakage in Embedding Models","created":"2020-03-31","cited_by_count":203},{"id":"2406.11944","title":"Transcoders Find Interpretable LLM Feature Circuits","created":"2024-06-17","cited_by_count":200},{"id":"2012.15816","title":"Fairness in Machine Learning","created":"2020-12-31","cited_by_count":194},{"id":"1906.09208","title":"Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practices","created":"2019-06-21","cited_by_count":174},{"id":"2010.12762","title":"Measuring Association Between Labels and Free-Text Rationales","created":"2020-10-24","cited_by_count":160},{"id":"2409.14507","title":"A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders","created":"2024-09-22","cited_by_count":160},{"id":"1909.07940","title":"Do NLP Models Know Numbers? Probing Numeracy in Embeddings","created":"2019-09-17","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":"2005.06247","title":"Explainable Reinforcement Learning: A Survey","created":"2020-05-13","cited_by_count":141},{"id":"1702.01932","title":"A Knowledge-Grounded Neural Conversation Model","created":"2017-02-07","cited_by_count":136},{"id":"2004.05773","title":"Generating Fact Checking Explanations","created":"2020-04-13","cited_by_count":132},{"id":"2108.05542","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","created":"2021-08-12","cited_by_count":131},{"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":"2402.18060","title":"Benchmarking Large Language Models on Answering and Explaining Challenging Medical Questions","created":"2024-02-28","cited_by_count":109},{"id":"1704.08006","title":"Deep Text Classification Can be Fooled","created":"2017-04-26","cited_by_count":106},{"id":"1910.13294","title":"Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control","created":"2019-10-29","cited_by_count":96},{"id":"1808.05697","title":"Deep Bayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Study","created":"2018-08-16","cited_by_count":90},{"id":"2001.02522","title":"On Interpretability of Artificial Neural Networks: A Survey","created":"2020-01-08","cited_by_count":88},{"id":"2008.06460","title":"Hate Speech Detection and Racial Bias Mitigation in Social Media based on BERT model","created":"2020-08-14","cited_by_count":87},{"id":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85},{"id":"1806.04185","title":"A Corpus with Multi-Level Annotations of Patients, Interventions and Outcomes to Support Language Processing for Medical Literature","created":"2018-06-11","cited_by_count":79},{"id":"2203.00870","title":"Faith-Shap: The Faithful Shapley Interaction Index","created":"2022-03-02","cited_by_count":69},{"id":"1801.05453","title":"Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs","created":"2018-01-16","cited_by_count":67},{"id":"2103.01907","title":"Fairness in Credit Scoring: Assessment, Implementation and Profit Implications","created":"2021-03-02","cited_by_count":65},{"id":"2005.01619","title":"From Arguments to Key Points: Towards Automatic Argument Summarization","created":"2020-05-04","cited_by_count":61},{"id":"2304.03347","title":"Towards Interpretable Mental Health Analysis with Large Language Models","created":"2023-04-06","cited_by_count":53},{"id":"1610.01256","title":"On the Safety of Machine Learning: Cyber-Physical Systems, Decision Sciences, and Data Products","created":"2016-10-05","cited_by_count":52},{"id":"2407.20371","title":"Gender, Race, and Intersectional Bias in Resume Screening via Language Model Retrieval","created":"2024-07-29","cited_by_count":51},{"id":"2405.03371","title":"Explainable Fake News Detection With Large Language Model via Defense Among Competing Wisdom","created":"2024-05-06","cited_by_count":50},{"id":"2303.04222","title":"SemEval-2023 Task 10: Explainable Detection of Online Sexism","created":"2023-03-07","cited_by_count":48},{"id":"1906.06187","title":"NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language","created":"2019-06-14","cited_by_count":37},{"id":"1805.11571","title":"Human-in-the-Loop Interpretability Prior","created":"2018-05-29","cited_by_count":36},{"id":"2110.13880","title":"Understanding Interlocking Dynamics of Cooperative Rationalization","created":"2021-10-26","cited_by_count":36},{"id":"2006.12166","title":"Open Source Software for Efficient and Transparent Reviews","created":"2020-06-22","cited_by_count":35},{"id":"2107.02975","title":"Neural Natural Language Processing for Unstructured Data in Electronic Health Records: a Review","created":"2021-07-07","cited_by_count":35},{"id":"2312.05491","title":"Using Captum to Explain Generative Language Models","created":"2023-12-09","cited_by_count":33},{"id":"2112.08802","title":"UNIREX: A Unified Learning Framework for Language Model Rationale Extraction","created":"2021-12-16","cited_by_count":32},{"id":"2311.00321","title":"HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning","created":"2023-11-01","cited_by_count":31},{"id":"2011.05268","title":"Towards Interpretable Natural Language Understanding with Explanations as Latent Variables","created":"2020-10-24","cited_by_count":30},{"id":"2111.01515","title":"Detection of Hate Speech using BERT and Hate Speech Word Embedding with Deep Model","created":"2021-11-02","cited_by_count":26},{"id":"2110.04399","title":"Global Explainability of BERT-Based Evaluation Metrics by Disentangling along Linguistic Factors","created":"2021-10-08","cited_by_count":25},{"id":"2106.13876","title":"Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations","created":"2021-06-25","cited_by_count":24},{"id":"1904.04063","title":"Analyzing and Interpreting Neural Networks for NLP: A Report on the First BlackboxNLP Workshop","created":"2019-04-05","cited_by_count":22},{"id":"2108.12197","title":"Translation Error Detection as Rationale Extraction","created":"2021-08-27","cited_by_count":22},{"id":"2301.08912","title":"Rationalization for Explainable NLP: A Survey","created":"2023-01-21","cited_by_count":22},{"id":"2012.15482","title":"FiD-Ex: Improving Sequence-to-Sequence Models for Extractive Rationale Generation","created":"2020-12-31","cited_by_count":21},{"id":"1909.00326","title":"Towards Understanding Neural Machine Translation with Word Importance","created":"2019-09-01","cited_by_count":19},{"id":"2103.00949","title":"Explainable AI in Credit Risk Management","created":"2021-03-01","cited_by_count":19},{"id":"2105.04837","title":"Rationalization through Concepts","created":"2021-05-11","cited_by_count":19}],"next_cursor":"100"}