{"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":"2305.18029","title":"Faithfulness Tests for Natural Language Explanations","created":"2023-05-29","cited_by_count":107,"area":null},{"id":"2207.00056","title":"MultiViz: Towards Visualizing and Understanding Multimodal Models","created":"2022-06-30","cited_by_count":36,"area":null},{"id":"2405.01379","title":"Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving","created":"2024-05-02","cited_by_count":35,"area":null},{"id":"2309.08395","title":"Learning by Self-Explaining","created":"2023-09-15","cited_by_count":17,"area":null},{"id":"2504.12691","title":"Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations","created":"2025-04-17","cited_by_count":15,"area":null},{"id":"2502.18848","title":"A Causal Lens for Evaluating Faithfulness Metrics","created":"2025-02-26","cited_by_count":12,"area":null},{"id":"2205.08696","title":"The Solvability of Interpretability Evaluation Metrics","created":"2022-05-18","cited_by_count":11,"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":"2308.14272","title":"Goodhart's Law Applies to NLP's Explanation Benchmarks","created":"2023-08-28","cited_by_count":10,"area":null},{"id":"2404.18533","title":"Evaluating Readability and Faithfulness of Concept-based Explanations","created":"2024-04-29","cited_by_count":10,"area":null},{"id":"2309.16223","title":"GInX-Eval: Towards In-Distribution Evaluation of Graph Neural Network Explanations","created":"2023-09-28","cited_by_count":9,"area":null},{"id":"2209.10876","title":"An Attention Matrix for Every Decision: Faithfulness-based Arbitration Among Multiple Attention-Based Interpretations of Transformers in Text Classification","created":"2022-09-22","cited_by_count":6,"area":null},{"id":"2405.05348","title":"The Effect of Model Size on LLM Post-hoc Explainability via LIME","created":"2024-05-08","cited_by_count":4,"area":null},{"id":"2504.02911","title":"Noiser: Bounded Input Perturbations for Attributing Large Language Models","created":"2025-04-03","cited_by_count":4,"area":null},{"id":"2408.11252","title":"Counterfactuals As a Means for Evaluating Faithfulness of Attribution Methods in Autoregressive Language Models","created":"2024-08-21","cited_by_count":3,"area":null},{"id":"2410.01482","title":"One Wave To Explain Them All: A Unifying Perspective On Feature Attribution","created":"2024-10-02","cited_by_count":3,"area":null},{"id":"2508.07636","title":"Attribution Explanations for Deep Neural Networks: A Theoretical Perspective","created":"2025-08-11","cited_by_count":2,"area":null},{"id":"2212.03513","title":"Truthful Meta-Explanations for Local Interpretability of Machine Learning Models","created":"2022-12-07","cited_by_count":1,"area":null},{"id":"2408.00166","title":"Review of Explainable Graph-Based Recommender Systems","created":"2024-07-31","cited_by_count":1,"area":null},{"id":"2504.12197","title":"Beyond Patches: Mining Interpretable Part-Prototypes for Explainable AI","created":"2025-04-16","cited_by_count":1,"area":null},{"id":"2511.15371","title":"CID: Measuring Feature Importance Through Counterfactual Distributions","created":"2025-11-19","cited_by_count":1,"area":null},{"id":"2601.12660","title":"Toward Faithful Explanations in Acoustic Anomaly Detection","created":"2026-01-19","cited_by_count":1,"area":null},{"id":"2405.07916","title":"IMAFD: An Interpretable Multi-stage Approach to Flood Detection from time series Multispectral Data","created":"2024-05-13","cited_by_count":0,"area":null},{"id":"2410.10290","title":"A Multi-Task Text Classification Pipeline with Natural Language Explanations: A User-Centric Evaluation in Sentiment Analysis and Offensive Language Identification in Greek Tweets","created":"2024-10-14","cited_by_count":0,"area":null},{"id":"2603.24828","title":"A Practical Guide Towards Interpreting Time-Series Deep Clinical Predictive Models: A Reproducibility Study","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2610.12493","title":"Faithfulness Without Anchors: A Position Paper on the Structural Misalignments of Explainable AI Faithfulness Metrics for Feature Importance","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}