{"total":13,"rows":[{"id":"2305.11391","title":"A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation","created":"2023-05-19","cited_by_count":93,"area":null},{"id":"2307.05902","title":"Stability Guarantees for Feature Attributions with Multiplicative Smoothing","created":"2023-07-12","cited_by_count":14,"area":null},{"id":"2406.04606","title":"Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions","created":"2024-06-07","cited_by_count":14,"area":null},{"id":"2305.12351","title":"Are Your Explanations Reliable? Investigating the Stability of LIME in Explaining Text Classifiers by Marrying XAI and Adversarial Attack","created":"2023-05-21","cited_by_count":10,"area":null},{"id":"2311.13735","title":"Surpassing GPT-4 Medical Coding with a Two-Stage Approach","created":"2023-11-22","cited_by_count":6,"area":null},{"id":"2211.04780","title":"On the Robustness of Explanations of Deep Neural Network Models: A Survey","created":"2022-11-09","cited_by_count":5,"area":null},{"id":"2312.17591","title":"Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Training","created":"2023-12-29","cited_by_count":4,"area":null},{"id":"2212.05327","title":"Identifying the Source of Vulnerability in Explanation Discrepancy: A Case Study in Neural Text Classification","created":"2022-12-10","cited_by_count":2,"area":null},{"id":"2212.09155","title":"Estimating the Adversarial Robustness of Attributions in Text with Transformers","created":"2022-12-18","cited_by_count":1,"area":null},{"id":"2307.02094","title":"DARE: Towards Robust Text Explanations in Biomedical and Healthcare Applications","created":"2023-07-05","cited_by_count":1,"area":null},{"id":"2308.06795","title":"Robust Infidelity: When Faithfulness Measures on Masked Language Models Are Misleading","created":"2023-08-13","cited_by_count":1,"area":null},{"id":"2501.01516","title":"Quantifying True Robustness: Synonymity-Weighted Similarity for Trustworthy XAI Evaluation","created":"2025-01-02","cited_by_count":1,"area":null},{"id":"2602.02763","title":"Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks","created":"2026-02-02","cited_by_count":0,"area":null}],"next_cursor":null}