{"total":42,"rows":[{"id":"2106.00786","title":"The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations","created":"2021-06-01","cited_by_count":87,"area":null},{"id":"2103.01378","title":"Contrastive Explanations for Model Interpretability","created":"2021-03-02","cited_by_count":75,"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":"2305.09770","title":"ConvXAI: Delivering Heterogeneous AI Explanations via Conversations to Support Human-AI Scientific Writing","created":"2023-05-16","cited_by_count":31,"area":null},{"id":"2207.10285","title":"Grounding Visual Representations with Texts for Domain Generalization","created":"2022-07-21","cited_by_count":30,"area":null},{"id":"2409.09951","title":"Optimal ablation for interpretability","created":"2024-09-16","cited_by_count":25,"area":null},{"id":"2204.10810","title":"Learning to Scaffold: Optimizing Model Explanations for Teaching","created":"2022-04-22","cited_by_count":20,"area":null},{"id":"2310.10266","title":"Generative Calibration for In-context Learning","created":"2023-10-16","cited_by_count":20,"area":null},{"id":"2110.10470","title":"Interpreting Deep Learning Models in Natural Language Processing: A Review","created":"2021-10-20","cited_by_count":19,"area":null},{"id":"2108.03388","title":"Jointly Attacking Graph Neural Network and its Explanations","created":"2021-08-07","cited_by_count":18,"area":null},{"id":"2109.05463","title":"Logic Traps in Evaluating Attribution Scores","created":"2021-09-12","cited_by_count":18,"area":null},{"id":"2205.03302","title":"Necessity and Sufficiency for Explaining Text Classifiers: A Case Study in Hate Speech Detection","created":"2022-05-06","cited_by_count":18,"area":null},{"id":"2102.13519","title":"PredDiff: Explanations and Interactions from Conditional Expectations","created":"2021-02-26","cited_by_count":17,"area":null},{"id":"2203.11131","title":"Towards Explainable Evaluation Metrics for Natural Language Generation","created":"2022-03-21","cited_by_count":15,"area":null},{"id":"2106.04753","title":"On Sample Based Explanation Methods for NLP:Efficiency, Faithfulness, and Semantic Evaluation","created":"2021-06-09","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":"2403.14459","title":"Multi-Level Explanations for Generative Language Models","created":"2024-03-21","cited_by_count":11,"area":null},{"id":"2408.03915","title":"Hard to Explain: On the Computational Hardness of In-Distribution Model Interpretation","created":"2024-08-07","cited_by_count":11,"area":null},{"id":"2104.08219","title":"Flexible Instance-Specific Rationalization of NLP Models","created":"2021-04-16","cited_by_count":10,"area":null},{"id":"2201.08802","title":"Deconfounding to Explanation Evaluation in Graph Neural Networks","created":"2022-01-21","cited_by_count":10,"area":null},{"id":"2403.06009","title":"Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations","created":"2024-03-09","cited_by_count":10,"area":null},{"id":"2205.13042","title":"How explainable are adversarially-robust CNNs?","created":"2022-05-25","cited_by_count":9,"area":null},{"id":"2405.20434","title":"Facilitating Human-LLM Collaboration through Factuality Scores and Source Attributions","created":"2024-05-30","cited_by_count":9,"area":null},{"id":"2306.12181","title":"Feature Interactions Reveal Linguistic Structure in Language Models","created":"2023-06-21","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":"2110.11929","title":"Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models?","created":"2021-10-22","cited_by_count":5,"area":null},{"id":"2202.09792","title":"Hierarchical Interpretation of Neural Text Classification","created":"2022-02-20","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":"2303.02860","title":"A Multi-Grained Self-Interpretable Symbolic-Neural Model For Single/Multi-Labeled Text Classification","created":"2023-03-06","cited_by_count":4,"area":null},{"id":"2605.17921","title":"An Efficient Streaming Video Understanding Framework with Agentic Control","created":"2026-05-18","cited_by_count":4,"area":null},{"id":"2306.03598","title":"CUE: An Uncertainty Interpretation Framework for Text Classifiers Built on Pre-Trained Language Models","created":"2023-06-06","cited_by_count":3,"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":"2103.03842","title":"Overcoming Poor Word Embeddings with Word Definitions","created":"2021-03-05","cited_by_count":1,"area":null},{"id":"2111.10100","title":"Does BERT look at sentiment lexicon?","created":"2021-11-19","cited_by_count":1,"area":null},{"id":"2306.13935","title":"Are Good Explainers Secretly Human-in-the-Loop Active Learners?","created":"2023-06-24","cited_by_count":1,"area":null},{"id":"2402.14702","title":"InfFeed: Influence Functions as a Feedback to Improve the Performance of Subjective Tasks","created":"2024-02-22","cited_by_count":1,"area":null},{"id":"2603.04831","title":"Missingness Bias Calibration in Feature Attribution Explanations","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2212.10469","title":"BMX: Boosting Natural Language Generation Metrics with Explainability","created":"2022-12-20","cited_by_count":0,"area":null},{"id":"2308.16588","title":"Interpreting Sentiment Composition with Latent Semantic Tree","created":"2023-08-31","cited_by_count":0,"area":null},{"id":"2404.02068","title":"Using Interpretation Methods for Model Enhancement","created":"2024-04-02","cited_by_count":0,"area":null},{"id":"2504.04640","title":"Splits! Flexible Sociocultural Linguistic Investigation at Scale","created":"2025-04-06","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}