{"total":22,"rows":[{"id":"2202.10419","title":"Interpreting Language Models with Contrastive Explanations","created":"2022-02-21","cited_by_count":92,"area":null},{"id":"2106.00786","title":"The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations","created":"2021-06-01","cited_by_count":87,"area":null},{"id":"2301.12971","title":"Quantifying Context Mixing in Transformers","created":"2023-01-30","cited_by_count":43,"area":null},{"id":"2103.07601","title":"Approximating How Single Head Attention Learns","created":"2021-03-13","cited_by_count":38,"area":null},{"id":"2105.03287","title":"Order in the Court: Explainable AI Methods Prone to Disagreement","created":"2021-05-07","cited_by_count":36,"area":null},{"id":"2212.03954","title":"Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning","created":"2022-12-07","cited_by_count":36,"area":null},{"id":"2205.12600","title":"ORCA: Interpreting Prompted Language Models via Locating Supporting Data Evidence in the Ocean of Pretraining Data","created":"2022-05-25","cited_by_count":34,"area":null},{"id":"2101.04109","title":"Explain and Predict, and then Predict Again","created":"2021-01-11","cited_by_count":29,"area":null},{"id":"2110.03212","title":"Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates","created":"2021-10-07","cited_by_count":27,"area":null},{"id":"2105.06977","title":"Do Context-Aware Translation Models Pay the Right Attention?","created":"2021-05-14","cited_by_count":21,"area":null},{"id":"2307.03859","title":"MDACE: MIMIC Documents Annotated with Code Evidence","created":"2023-07-07","cited_by_count":19,"area":null},{"id":"2112.02625","title":"Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution View","created":"2021-12-05","cited_by_count":15,"area":null},{"id":"2204.08892","title":"A survey on improving NLP models with human explanations","created":"2022-04-19","cited_by_count":15,"area":null},{"id":"2503.14421","title":"ExDDV: A New Dataset for Explainable Deepfake Detection in Video","created":"2025-03-18","cited_by_count":10,"area":null},{"id":"2210.07469","title":"StyLEx: Explaining Style Using Human Lexical Annotations","created":"2022-10-14","cited_by_count":3,"area":null},{"id":"2104.07894","title":"Faithful and Plausible Explanations of Medical Code Predictions","created":"2021-04-16","cited_by_count":2,"area":null},{"id":"2502.01270","title":"Main Predicate and Their Arguments as Explanation Signals For Intent Classification","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2502.20268","title":"Large Language Models as Attribution Regularizers for Efficient Model Training","created":"2025-02-27","cited_by_count":1,"area":null},{"id":"2308.16588","title":"Interpreting Sentiment Composition with Latent Semantic Tree","created":"2023-08-31","cited_by_count":0,"area":null},{"id":"2506.07168","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","created":"2025-06-08","cited_by_count":0,"area":null},{"id":"2507.21302","title":"Can human clinical rationales improve the performance and explainability of clinical text classification models?","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2508.01486","title":"Human-Centered Supervision for Sentiment Analysis in Telugu: A Systematic Inquiry Beyond Accuracy","created":"2025-08-02","cited_by_count":0,"area":null}],"next_cursor":null}