{"total":25,"rows":[{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2305.18029","title":"Faithfulness Tests for Natural Language Explanations","created":"2023-05-29","cited_by_count":107,"area":null},{"id":"2111.07367","title":"\"Will You Find These Shortcuts?\" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification","created":"2021-11-14","cited_by_count":66,"area":null},{"id":"2310.00603","title":"Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals","created":"2023-10-01","cited_by_count":44,"area":null},{"id":"2202.07728","title":"Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis","created":"2022-02-15","cited_by_count":38,"area":null},{"id":"2208.01575","title":"ferret: a Framework for Benchmarking Explainers on Transformers","created":"2022-08-02","cited_by_count":26,"area":null},{"id":"2211.13290","title":"SEAT: Stable and Explainable Attention","created":"2022-11-23","cited_by_count":25,"area":null},{"id":"2405.01461","title":"SATO: Stable Text-to-Motion Framework","created":"2024-05-02","cited_by_count":20,"area":null},{"id":"2410.02970","title":"F-Fidelity: A Robust Framework for Faithfulness Evaluation of Explainable AI","created":"2024-10-03","cited_by_count":18,"area":null},{"id":"2205.11097","title":"A Fine-grained Interpretability Evaluation Benchmark for Neural NLP","created":"2022-05-23","cited_by_count":15,"area":null},{"id":"2311.17983","title":"Improving Interpretation Faithfulness for Vision Transformers","created":"2023-11-29","cited_by_count":12,"area":null},{"id":"2407.00219","title":"Evaluating Human Alignment and Model Faithfulness of LLM Rationale","created":"2024-06-28","cited_by_count":12,"area":null},{"id":"2312.12747","title":"ALMANACS: A Simulatability Benchmark for Language Model Explainability","created":"2023-12-20","cited_by_count":11,"area":null},{"id":"2408.08137","title":"Normalized AOPC: Fixing Misleading Faithfulness Metrics for Feature Attribution Explainability","created":"2024-08-15","cited_by_count":10,"area":null},{"id":"2305.03601","title":"Human Attention-Guided Explainable Artificial Intelligence for Computer Vision Models","created":"2023-05-05","cited_by_count":6,"area":null},{"id":"2207.13948","title":"An Interpretability Evaluation Benchmark for Pre-trained Language Models","created":"2022-07-28","cited_by_count":4,"area":null},{"id":"2305.19998","title":"Efficient Shapley Values Estimation by Amortization for Text Classification","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2410.06950","title":"Faithful Interpretation for Graph Neural Networks","created":"2024-10-09","cited_by_count":3,"area":null},{"id":"2406.05588","title":"CERET: Cost-Effective Extrinsic Refinement for Text Generation","created":"2024-06-08","cited_by_count":1,"area":null},{"id":"2505.07005","title":"Explainable AI the Latest Advancements and New Trends","created":"2025-05-11","cited_by_count":1,"area":null},{"id":"2405.12222","title":"Influence based explainability of brain tumors segmentation in multimodal Magnetic Resonance Imaging","created":"2024-04-05","cited_by_count":0,"area":null},{"id":"2502.02786","title":"When Machine Learning Gets Personal: Evaluating Prediction and Explanation","created":"2025-02-05","cited_by_count":0,"area":null},{"id":"2503.02971","title":"Multilingual Relative Clause Attachment Ambiguity Resolution in Large Language Models","created":"2025-03-04","cited_by_count":0,"area":null},{"id":"2503.04989","title":"Application of integrated gradients explainability to sociopsychological semantic markers","created":"2025-03-06","cited_by_count":0,"area":null},{"id":"2601.03089","title":"Faithfulness Evaluation for Decoder-only LLM Attributions with Controlled Retained Information","created":"2026-01-06","cited_by_count":0,"area":null}],"next_cursor":null}