{"total":34,"rows":[{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"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":"2104.08782","title":"On the Sensitivity and Stability of Model Interpretations in NLP","created":"2021-04-18","cited_by_count":30,"area":null},{"id":"2407.14962","title":"Recent Advances in Generative AI and Large Language Models: Current Status, Challenges, and Perspectives","created":"2024-07-20","cited_by_count":30,"area":null},{"id":"2106.03471","title":"Relative Importance in Sentence Processing","created":"2021-06-07","cited_by_count":22,"area":null},{"id":"2110.14297","title":"Revisiting Sanity Checks for Saliency Maps","created":"2021-10-27","cited_by_count":20,"area":null},{"id":"2109.05463","title":"Logic Traps in Evaluating Attribution Scores","created":"2021-09-12","cited_by_count":18,"area":null},{"id":"2109.01962","title":"Counterfactual Evaluation for Explainable AI","created":"2021-09-05","cited_by_count":15,"area":null},{"id":"2201.11239","title":"Diagnosing AI Explanation Methods with Folk Concepts of Behavior","created":"2022-01-27","cited_by_count":15,"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":"2205.04559","title":"A Song of (Dis)agreement: Evaluating the Evaluation of Explainable Artificial Intelligence in Natural Language Processing","created":"2022-05-09","cited_by_count":13,"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":"2206.02958","title":"Saliency Cards: A Framework to Characterize and Compare Saliency Methods","created":"2022-06-07","cited_by_count":11,"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":"2108.13140","title":"DuTrust: A Sentiment Analysis Dataset for Trustworthiness Evaluation","created":"2021-08-30","cited_by_count":5,"area":null},{"id":"2204.05428","title":"A Multilingual Perspective Towards the Evaluation of Attribution Methods in Natural Language Inference","created":"2022-04-11","cited_by_count":5,"area":null},{"id":"2110.02058","title":"Interactively Providing Explanations for Transformer Language Models","created":"2021-09-02","cited_by_count":4,"area":null},{"id":"2203.01146","title":"Controlling the Focus of Pretrained Language Generation Models","created":"2022-03-02","cited_by_count":4,"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":"2310.05619","title":"Dynamic Top-k Estimation Consolidates Disagreement between Feature Attribution Methods","created":"2023-10-09","cited_by_count":4,"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":"2509.21631","title":"Towards Transparent AI: A Survey on Explainable Language Models","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2205.15581","title":"Comparing interpretation methods in mental state decoding analyses with deep learning models","created":"2022-05-31","cited_by_count":2,"area":null},{"id":"2312.11507","title":"Explain To Decide: A Human-Centric Review on the Role of Explainable Artificial Intelligence in AI-assisted Decision Making","created":"2023-12-11","cited_by_count":2,"area":null},{"id":"2404.07725","title":"Unraveling the Dilemma of AI Errors: Exploring the Effectiveness of Human and Machine Explanations for Large Language Models","created":"2024-04-11","cited_by_count":2,"area":null},{"id":"2601.14152","title":"Lost in the Prompt Order: Revealing the Limitations of Causal Attention in Language Models","created":"2026-01-20","cited_by_count":2,"area":null},{"id":"2303.16537","title":"LMExplainer: Grounding Knowledge and Explaining Language Models","created":"2023-03-29","cited_by_count":1,"area":null},{"id":"2310.06654","title":"Evaluating Explanation Methods for Vision-and-Language Navigation","created":"2023-10-10","cited_by_count":1,"area":null},{"id":"2310.13506","title":"Explaining Interactions Between Text Spans","created":"2023-10-20","cited_by_count":1,"area":null},{"id":"2403.05338","title":"Explaining Pre-Trained Language Models with Attribution Scores: An Analysis in Low-Resource Settings","created":"2024-03-08","cited_by_count":1,"area":null},{"id":"2405.10767","title":"Evaluating Saliency Explanations in NLP by Crowdsourcing","created":"2024-05-17","cited_by_count":1,"area":null},{"id":"2410.14894","title":"Soft-Label Integration for Robust Toxicity Classification","created":"2024-10-18","cited_by_count":1,"area":null},{"id":"2508.01892","title":"How Does Controllability Emerge In Language Models During Pretraining?","created":"2025-08-03","cited_by_count":0,"area":null},{"id":"2604.12321","title":"ToxiTrace: Gradient-Aligned Training for Explainable Chinese Toxicity Detection","created":"2026-04-14","cited_by_count":0,"area":null}],"next_cursor":null}