{"total":28,"rows":[{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2309.07311","title":"Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs","created":"2023-09-13","cited_by_count":124,"area":null},{"id":"2207.07605","title":"Algorithms to estimate Shapley value feature attributions","created":"2022-07-15","cited_by_count":115,"area":null},{"id":"2206.05282","title":"Learning to Estimate Shapley Values with Vision Transformers","created":"2022-06-10","cited_by_count":45,"area":null},{"id":"2201.12114","title":"Rethinking Attention-Model Explainability through Faithfulness Violation Test","created":"2022-01-28","cited_by_count":43,"area":null},{"id":"2312.12141","title":"Neuron-Level Knowledge Attribution in Large Language Models","created":"2023-12-19","cited_by_count":37,"area":null},{"id":"2305.13417","title":"VISIT: Visualizing and Interpreting the Semantic Information Flow of Transformers","created":"2023-05-22","cited_by_count":32,"area":null},{"id":"2402.01704","title":"Steering Language Models with Game-Theoretic Solvers","created":"2024-01-24","cited_by_count":28,"area":null},{"id":"2404.09554","title":"Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda","created":"2024-04-15","cited_by_count":22,"area":null},{"id":"2201.11239","title":"Diagnosing AI Explanation Methods with Folk Concepts of Behavior","created":"2022-01-27","cited_by_count":15,"area":null},{"id":"2205.04559","title":"A Song of (Dis)agreement: Evaluating the Evaluation of Explainable Artificial Intelligence in Natural Language Processing","created":"2022-05-09","cited_by_count":13,"area":null},{"id":"2402.03485","title":"Attention Meets Post-hoc Interpretability: A Mathematical Perspective","created":"2024-02-05","cited_by_count":11,"area":null},{"id":"2212.03044","title":"On the Importance of Clinical Notes in Multi-modal Learning for EHR Data","created":"2022-12-06","cited_by_count":10,"area":null},{"id":"2306.06205","title":"Morphosyntactic probing of multilingual BERT models","created":"2023-06-09","cited_by_count":8,"area":null},{"id":"2210.05098","title":"IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces","created":"2022-10-11","cited_by_count":7,"area":null},{"id":"2402.18678","title":"RORA: Robust Free-Text Rationale Evaluation","created":"2024-02-28","cited_by_count":4,"area":null},{"id":"2502.15765","title":"Generalized Attention Flow: Feature Attribution for Transformer Models via Maximum Flow","created":"2025-02-14","cited_by_count":4,"area":null},{"id":"2501.06248","title":"Utility-inspired Reward Transformations Improve Reinforcement Learning Training of Language Models","created":"2025-01-08","cited_by_count":2,"area":null},{"id":"2502.03418","title":"Which Words Matter Most in Zero-Shot Prompts?","created":"2025-02-05","cited_by_count":2,"area":null},{"id":"2205.15389","title":"Attention Flows for General Transformers","created":"2022-05-30","cited_by_count":1,"area":null},{"id":"2211.15924","title":"Weakly Supervised Learning Significantly Reduces the Number of Labels Required for Intracranial Hemorrhage Detection on Head CT","created":"2022-11-29","cited_by_count":1,"area":null},{"id":"2403.13106","title":"Using Shapley interactions to understand how models use structure","created":"2024-03-19","cited_by_count":1,"area":null},{"id":"2411.02610","title":"Investigating Idiomaticity in Word Representations","created":"2024-11-04","cited_by_count":1,"area":null},{"id":"2311.06311","title":"Game Theory Solutions in Sensor-Based Human Activity Recognition: A Review","created":"2023-11-09","cited_by_count":0,"area":null},{"id":"2502.02109","title":"Causally-informed Deep Learning towards Explainable and Generalizable Outcomes Prediction in Critical Care","created":"2025-02-04","cited_by_count":0,"area":null},{"id":"2507.11855","title":"OrdShap: Feature Position Importance for Sequential Black-Box Models","created":"2025-07-16","cited_by_count":0,"area":null},{"id":"2508.08966","title":"Integrating attention into explanation frameworks for language and vision transformers","created":"2025-08-12","cited_by_count":0,"area":null}],"next_cursor":null}