{"total":27,"rows":[{"id":"2306.06123","title":"Adversarial attacks and defenses in explainable artificial intelligence: A survey","created":"2023-06-06","cited_by_count":48,"area":null},{"id":"2406.19470","title":"Changing Answer Order Can Decrease MMLU Accuracy","created":"2024-06-27","cited_by_count":42,"area":null},{"id":"2211.16080","title":"Understanding and Enhancing Robustness of Concept-based Models","created":"2022-11-29","cited_by_count":22,"area":null},{"id":"2109.05463","title":"Logic Traps in Evaluating Attribution Scores","created":"2021-09-12","cited_by_count":18,"area":null},{"id":"2206.03178","title":"Fooling Explanations in Text Classifiers","created":"2022-06-07","cited_by_count":13,"area":null},{"id":"2412.13989","title":"What makes a good metric? Evaluating automatic metrics for text-to-image consistency","created":"2024-12-18","cited_by_count":12,"area":null},{"id":"2108.13961","title":"Thermostat: A Large Collection of NLP Model Explanations and Analysis Tools","created":"2021-08-31","cited_by_count":11,"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":"2207.06897","title":"Beware the Rationalization Trap! When Language Model Explainability Diverges from our Mental Models of Language","created":"2022-07-14","cited_by_count":9,"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":"2403.12809","title":"Comparing Explanation Faithfulness between Multilingual and Monolingual Fine-tuned Language Models","created":"2024-03-19","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":"2407.19683","title":"Revisiting the robustness of post-hoc interpretability methods","created":"2024-07-29","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":"2405.00349","title":"A Self-explaining Neural Architecture for Generalizable Concept Learning","created":"2024-05-01","cited_by_count":3,"area":null},{"id":"2504.07274","title":"Language Modeling for the Future of Finance: A Survey into Metrics, Tasks, and Data Opportunities","created":"2025-04-09","cited_by_count":3,"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":"2405.08468","title":"Challenges and Opportunities in Text Generation Explainability","created":"2024-05-14","cited_by_count":2,"area":null},{"id":"2409.17774","title":"Faithfulness and the Notion of Adversarial Sensitivity in NLP Explanations","created":"2024-09-26","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":"2406.15839","title":"The Effect of Similarity Measures on Accurate Stability Estimates for Local Surrogate Models in Text-based Explainable AI","created":"2024-06-22","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":"2501.02042","title":"Towards Robust and Accurate Stability Estimation of Local Surrogate Models in Text-based Explainable AI","created":"2025-01-03","cited_by_count":1,"area":null},{"id":"2506.14613","title":"When Does Meaning Backfire? Investigating the Role of AMRs in NLI","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2605.21726","title":"Probabilistic Attribution For Large Language Models","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2407.01697","title":"NLPGuard: A Framework for Mitigating the Use of Protected Attributes by NLP Classifiers","created":"2024-07-01","cited_by_count":0,"area":null}],"next_cursor":null}