{"total":39,"rows":[{"id":"2112.07566","title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","created":"2021-12-14","cited_by_count":135,"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":"2106.02666","title":"Counterfactual Explanations Can Be Manipulated","created":"2021-06-04","cited_by_count":113,"area":null},{"id":"2202.00734","title":"Framework for Evaluating Faithfulness of Local Explanations","created":"2022-02-01","cited_by_count":55,"area":null},{"id":"2202.01875","title":"Rethinking Explainability as a Dialogue: A Practitioner's Perspective","created":"2022-02-03","cited_by_count":52,"area":null},{"id":"2403.10415","title":"Gradient based Feature Attribution in Explainable AI: A Technical Review","created":"2024-03-15","cited_by_count":34,"area":null},{"id":"2206.07023","title":"SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features","created":"2022-06-14","cited_by_count":33,"area":null},{"id":"2306.02873","title":"DecompX: Explaining Transformers Decisions by Propagating Token Decomposition","created":"2023-06-05","cited_by_count":31,"area":null},{"id":"2108.04990","title":"Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing","created":"2021-08-11","cited_by_count":30,"area":null},{"id":"2109.06387","title":"Rationales for Sequential Predictions","created":"2021-09-14","cited_by_count":26,"area":null},{"id":"2201.11569","title":"Human Interpretation of Saliency-based Explanation Over Text","created":"2022-01-27","cited_by_count":25,"area":null},{"id":"2109.05463","title":"Logic Traps in Evaluating Attribution Scores","created":"2021-09-12","cited_by_count":18,"area":null},{"id":"2305.06754","title":"COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP tasks","created":"2023-05-11","cited_by_count":16,"area":null},{"id":"2105.05641","title":"How Reliable are Model Diagnostics?","created":"2021-05-12","cited_by_count":13,"area":null},{"id":"2107.01943","title":"When and How to Fool Explainable Models (and Humans) with Adversarial Examples","created":"2021-07-05","cited_by_count":10,"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":"2203.17081","title":"Interpretation of Black Box NLP Models: A Survey","created":"2022-03-31","cited_by_count":9,"area":null},{"id":"2304.11721","title":"A Lightweight Constrained Generation Alternative for Query-focused Summarization","created":"2023-04-23","cited_by_count":8,"area":null},{"id":"2310.05703","title":"An Attribution Method for Siamese Encoders","created":"2023-10-09","cited_by_count":8,"area":null},{"id":"2312.01582","title":"Explaining with Contrastive Phrasal Highlighting: A Case Study in Assisting Humans to Detect Translation Differences","created":"2023-12-04","cited_by_count":8,"area":null},{"id":"2501.04802","title":"Reproducing HotFlip for Corpus Poisoning Attacks in Dense Retrieval","created":"2025-01-08","cited_by_count":7,"area":null},{"id":"2204.11424","title":"It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation Classifiers","created":"2022-04-25","cited_by_count":5,"area":null},{"id":"2205.10238","title":"Visualizing and Explaining Language Models","created":"2022-04-30","cited_by_count":4,"area":null},{"id":"2305.02679","title":"Neighboring Words Affect Human Interpretation of Saliency Explanations","created":"2023-05-04","cited_by_count":4,"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":"2411.16252","title":"NormXLogit: The Head-on-Top Never Lies","created":"2024-11-25","cited_by_count":4,"area":null},{"id":"2205.09620","title":"Towards a Theory of Faithfulness: Faithful Explanations of Differentiable Classifiers over Continuous Data","created":"2022-05-19","cited_by_count":3,"area":null},{"id":"2208.06096","title":"Comparing Baseline Shapley and Integrated Gradients for Local Explanation: Some Additional Insights","created":"2022-08-12","cited_by_count":3,"area":null},{"id":"2211.08425","title":"A Rigorous Study Of The Deep Taylor Decomposition","created":"2022-11-14","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":"2302.10479","title":"Tell Model Where to Attend: Improving Interpretability of Aspect-Based Sentiment Classification via Small Explanation Annotations","created":"2023-02-21","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":"2502.03418","title":"Which Words Matter Most in Zero-Shot Prompts?","created":"2025-02-05","cited_by_count":2,"area":null},{"id":"2303.14116","title":"Improving Prediction Performance and Model Interpretability through Attention Mechanisms from Basic and Applied Research Perspectives","created":"2023-03-24","cited_by_count":0,"area":null},{"id":"2306.02043","title":"Painsight: An Extendable Opinion Mining Framework for Detecting Pain Points Based on Online Customer Reviews","created":"2023-06-03","cited_by_count":0,"area":null},{"id":"2406.10213","title":"Selecting Interpretability Techniques for Healthcare Machine Learning models","created":"2024-06-14","cited_by_count":0,"area":null},{"id":"2410.12511","title":"Advancing Fairness in Natural Language Processing: From Traditional Methods to Explainability","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2506.14203","title":"Intended Target Identification for Anomia Patients with Gradient-based Selective Augmentation","created":"2025-06-17","cited_by_count":0,"area":null},{"id":"2609.28117","title":"Scaling Attention Head Analysis via Gradient-Based Attribution in Context-Aware Machine Translation","created":"2026-09-23","cited_by_count":0,"area":null}],"next_cursor":null}