{"total":25,"rows":[{"id":"2212.14855","title":"Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces","created":"2022-12-30","cited_by_count":25,"area":null},{"id":"2311.02805","title":"Tailoring Self-Rationalizers with Multi-Reward Distillation","created":"2023-11-06","cited_by_count":21,"area":null},{"id":"2111.03536","title":"A Unified Game-Theoretic Interpretation of Adversarial Robustness","created":"2021-11-05","cited_by_count":17,"area":null},{"id":"2108.06895","title":"Interpreting Attributions and Interactions of Adversarial Attacks","created":"2021-08-16","cited_by_count":13,"area":null},{"id":"2403.14459","title":"Multi-Level Explanations for Generative Language Models","created":"2024-03-21","cited_by_count":11,"area":null},{"id":"2105.10719","title":"Can We Faithfully Represent Masked States to Compute Shapley Values on a DNN?","created":"2021-05-22","cited_by_count":10,"area":null},{"id":"2309.11960","title":"A Comprehensive Review on Financial Explainable AI","created":"2023-09-21","cited_by_count":10,"area":null},{"id":"2106.01809","title":"Exploring Distantly-Labeled Rationales in Neural Network Models","created":"2021-06-03","cited_by_count":8,"area":null},{"id":"2306.12181","title":"Feature Interactions Reveal Linguistic Structure in Language Models","created":"2023-06-21","cited_by_count":8,"area":null},{"id":"2205.12542","title":"ER-Test: Evaluating Explanation Regularization Methods for Language Models","created":"2022-05-25","cited_by_count":6,"area":null},{"id":"2103.03103","title":"Interpretable Artificial Intelligence through the Lens of Feature Interaction","created":"2021-03-01","cited_by_count":5,"area":null},{"id":"2202.09792","title":"Hierarchical Interpretation of Neural Text Classification","created":"2022-02-20","cited_by_count":5,"area":null},{"id":"2203.12536","title":"Dynamically Refined Regularization for Improving Cross-corpora Hate Speech Detection","created":"2022-03-23","cited_by_count":3,"area":null},{"id":"2402.17914","title":"Extracting Lexical Features from Dialects via Interpretable Dialect Classifiers","created":"2024-02-27","cited_by_count":3,"area":null},{"id":"2406.16672","title":"CAVE: Controllable Authorship Verification Explanations","created":"2024-06-24","cited_by_count":3,"area":null},{"id":"2210.03080","title":"Explainable Verbal Deception Detection using Transformers","created":"2022-10-06","cited_by_count":2,"area":null},{"id":"2410.17546","title":"Advancing Interpretability in Text Classification through Prototype Learning","created":"2024-10-23","cited_by_count":2,"area":null},{"id":"2109.04726","title":"AutoTriggER: Label-Efficient and Robust Named Entity Recognition with Auxiliary Trigger Extraction","created":"2021-09-10","cited_by_count":1,"area":null},{"id":"2203.07640","title":"Unsupervised Keyphrase Extraction via Interpretable Neural Networks","created":"2022-03-15","cited_by_count":1,"area":null},{"id":"2411.16251","title":"Transparent Neighborhood Approximation for Text Classifier Explanation","created":"2024-11-25","cited_by_count":1,"area":null},{"id":"2103.07364","title":"A Unified Game-Theoretic Interpretation of Adversarial Robustness","created":"2021-03-12","cited_by_count":0,"area":null},{"id":"2209.08681","title":"Domain Classification-based Source-specific Term Penalization for Domain Adaptation in Hate-speech Detection","created":"2022-09-18","cited_by_count":0,"area":null},{"id":"2403.16554","title":"PE: A Poincare Explanation Method for Fast Text Hierarchy Generation","created":"2024-03-25","cited_by_count":0,"area":null},{"id":"2412.01644","title":"Concept Based Continuous Prompts for Interpretable Text Classification","created":"2024-12-02","cited_by_count":0,"area":null},{"id":"2507.10596","title":"PLEX: Perturbation-free Local Explanations for LLM-Based Text Classification","created":"2025-07-12","cited_by_count":0,"area":null}],"next_cursor":null}