{"total":111,"rows":[{"id":"2108.11896","title":"A Survey on Automated Fact-Checking","created":"2021-08-26","cited_by_count":378,"area":null},{"id":"2201.08164","title":"From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI","created":"2022-01-20","cited_by_count":302,"area":null},{"id":"2301.13379","title":"Faithful Chain-of-Thought Reasoning","created":"2023-01-31","cited_by_count":288,"area":"lr"},{"id":"2101.00288","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","created":"2021-01-01","cited_by_count":222,"area":null},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156,"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":"2104.14403","title":"Do Feature Attribution Methods Correctly Attribute Features?","created":"2021-04-27","cited_by_count":98,"area":null},{"id":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91,"area":null},{"id":"2110.07736","title":"Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models","created":"2021-10-14","cited_by_count":76,"area":null},{"id":"2203.04212","title":"Measuring the Mixing of Contextual Information in the Transformer","created":"2022-03-08","cited_by_count":65,"area":null},{"id":"2310.04959","title":"Towards Better Chain-of-Thought Prompting Strategies: A Survey","created":"2023-10-08","cited_by_count":62,"area":"lr"},{"id":"2208.05309","title":"Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation","created":"2022-08-10","cited_by_count":61,"area":null},{"id":"2103.12279","title":"SelfExplain: A Self-Explaining Architecture for Neural Text Classifiers","created":"2021-03-23","cited_by_count":44,"area":null},{"id":"2305.12535","title":"Explaining How Transformers Use Context to Build Predictions","created":"2023-05-21","cited_by_count":43,"area":null},{"id":"2204.11073","title":"Grad-SAM: Explaining Transformers via Gradient Self-Attention Maps","created":"2022-04-23","cited_by_count":42,"area":null},{"id":"2111.04683","title":"Revisiting Methods for Finding Influential Examples","created":"2021-11-08","cited_by_count":39,"area":null},{"id":"2103.07601","title":"Approximating How Single Head Attention Learns","created":"2021-03-13","cited_by_count":38,"area":null},{"id":"2210.06929","title":"On the Explainability of Natural Language Processing Deep Models","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2105.15164","title":"DISSECT: Disentangled Simultaneous Explanations via Concept Traversals","created":"2021-05-31","cited_by_count":37,"area":null},{"id":"2105.03287","title":"Order in the Court: Explainable AI Methods Prone to Disagreement","created":"2021-05-07","cited_by_count":36,"area":null},{"id":"2110.13880","title":"Understanding Interlocking Dynamics of Cooperative Rationalization","created":"2021-10-26","cited_by_count":36,"area":null},{"id":"2207.00056","title":"MultiViz: Towards Visualizing and Understanding Multimodal Models","created":"2022-06-30","cited_by_count":36,"area":null},{"id":"2105.08621","title":"Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networks","created":"2021-05-18","cited_by_count":35,"area":null},{"id":"2502.17516","title":"A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models","created":"2025-02-22","cited_by_count":34,"area":"mllm"},{"id":"2106.01087","title":"Is Sparse Attention more Interpretable?","created":"2021-06-02","cited_by_count":31,"area":null},{"id":"2110.08412","title":"Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining","created":"2021-10-15","cited_by_count":31,"area":null},{"id":"2105.07542","title":"Collaborative Graph Learning with Auxiliary Text for Temporal Event Prediction in Healthcare","created":"2021-05-16","cited_by_count":30,"area":null},{"id":"2406.12053","title":"InternalInspector $I^2$: Robust Confidence Estimation in LLMs through Internal States","created":"2024-06-17","cited_by_count":30,"area":null},{"id":"2105.02657","title":"Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification","created":"2021-05-06","cited_by_count":29,"area":null},{"id":"2207.00938","title":"Interpretable by Design: Learning Predictors by Composing Interpretable Queries","created":"2022-07-03","cited_by_count":28,"area":null},{"id":"2211.03064","title":"ViT-CX: Causal Explanation of Vision Transformers","created":"2022-11-06","cited_by_count":28,"area":null},{"id":"2104.06709","title":"Towards BERT-based Automatic ICD Coding: Limitations and Opportunities","created":"2021-04-14","cited_by_count":25,"area":null},{"id":"2111.05711","title":"Counterfactual Explanations for Models of Code","created":"2021-11-10","cited_by_count":25,"area":null},{"id":"2209.11812","title":"Explanations, Fairness, and Appropriate Reliance in Human-AI Decision-Making","created":"2022-09-23","cited_by_count":25,"area":null},{"id":"2312.03656","title":"Interpretability Illusions in the Generalization of Simplified Models","created":"2023-12-06","cited_by_count":25,"area":null},{"id":"2411.15102","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","created":"2024-11-22","cited_by_count":23,"area":null},{"id":"2204.05426","title":"ProtoTEx: Explaining Model Decisions with Prototype Tensors","created":"2022-04-11","cited_by_count":21,"area":null},{"id":"2206.03529","title":"How to Dissect a Muppet: The Structure of Transformer Embedding Spaces","created":"2022-06-07","cited_by_count":20,"area":null},{"id":"2105.04837","title":"Rationalization through Concepts","created":"2021-05-11","cited_by_count":19,"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":"2109.05463","title":"Logic Traps in Evaluating Attribution Scores","created":"2021-09-12","cited_by_count":18,"area":null},{"id":"2501.15638","title":"A Comprehensive Survey on Self-Interpretable Neural Networks","created":"2025-01-26","cited_by_count":18,"area":null},{"id":"2101.04547","title":"Of Non-Linearity and Commutativity in BERT","created":"2021-01-12","cited_by_count":16,"area":null},{"id":"2105.03928","title":"Which transformer architecture fits my data? A vocabulary bottleneck in self-attention","created":"2021-05-09","cited_by_count":16,"area":null},{"id":"2108.13759","title":"Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience","created":"2021-08-31","cited_by_count":16,"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":"2210.12330","title":"Salience Allocation as Guidance for Abstractive Summarization","created":"2022-10-22","cited_by_count":14,"area":null},{"id":"2105.05641","title":"How Reliable are Model Diagnostics?","created":"2021-05-12","cited_by_count":13,"area":null},{"id":"2109.05853","title":"Attention Weights in Transformer NMT Fail Aligning Words Between Sequences but Largely Explain Model Predictions","created":"2021-09-13","cited_by_count":11,"area":null},{"id":"2403.11894","title":"From Explainable to Interpretable Deep Learning for Natural Language Processing in Healthcare: How Far from Reality?","created":"2024-03-18","cited_by_count":11,"area":null},{"id":"2602.08783","title":"Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure","created":"2026-02-09","cited_by_count":11,"area":"lr"},{"id":"2106.01518","title":"Dissecting Generation Modes for Abstractive Summarization Models via Ablation and Attribution","created":"2021-06-03","cited_by_count":10,"area":null},{"id":"2111.14651","title":"Multi-objective Explanations of GNN Predictions","created":"2021-11-29","cited_by_count":10,"area":null},{"id":"2305.17627","title":"Robust Natural Language Understanding with Residual Attention Debiasing","created":"2023-05-28","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":"2104.08763","title":"Making Attention Mechanisms More Robust and Interpretable with Virtual Adversarial Training","created":"2021-04-18","cited_by_count":8,"area":null},{"id":"2211.13236","title":"MEGAN: Multi-Explanation Graph Attention Network","created":"2022-11-23","cited_by_count":7,"area":null},{"id":"2403.20322","title":"Towards a Framework for Evaluating Explanations in Automated Fact Verification","created":"2024-03-29","cited_by_count":7,"area":null},{"id":"2104.11026","title":"MeSIN: Multilevel Selective and Interactive Network for Medication Recommendation","created":"2021-04-22","cited_by_count":6,"area":null},{"id":"2109.03756","title":"Diagnostics-Guided Explanation Generation","created":"2021-09-08","cited_by_count":6,"area":null},{"id":"2405.20404","title":"JoPA:Explaining Large Language Model's Generation via Joint Prompt Attribution","created":"2024-05-30","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":"2112.05125","title":"Rethinking the Authorship Verification Experimental Setups","created":"2021-12-09","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":"2204.09852","title":"The Risks of Machine Learning Systems","created":"2022-04-21","cited_by_count":5,"area":null},{"id":"2308.05219","title":"Decoding Layer Saliency in Language Transformers","created":"2023-08-09","cited_by_count":5,"area":null},{"id":"2507.01936","title":"The Thin Line Between Comprehension and Persuasion in LLMs","created":"2025-07-02","cited_by_count":5,"area":null},{"id":"2601.10266","title":"Measuring Affinity between Attention-Head Weight Subspaces via the Projection Kernel","created":"2026-01-15","cited_by_count":5,"area":null},{"id":"2604.16242","title":"Detecting and Suppressing Reward Hacking with Gradient Fingerprints","created":"2026-04-17","cited_by_count":5,"area":"alignment"},{"id":"2110.12148","title":"Event Detection on Dynamic Graphs","created":"2021-10-23","cited_by_count":4,"area":null},{"id":"2204.13156","title":"On the Relationship Between Explanations, Fairness Perceptions, and Decisions","created":"2022-04-27","cited_by_count":4,"area":null},{"id":"2310.02588","title":"ViT-ReciproCAM: Gradient and Attention-Free Visual Explanations for Vision Transformer","created":"2023-10-04","cited_by_count":4,"area":null},{"id":"2310.14418","title":"REFER: An End-to-end Rationale Extraction Framework for Explanation Regularization","created":"2023-10-22","cited_by_count":4,"area":null},{"id":"2312.16191","title":"SoK: Taming the Triangle -- On the Interplays between Fairness, Interpretability and Privacy in Machine Learning","created":"2023-12-22","cited_by_count":4,"area":null},{"id":"2402.18678","title":"RORA: Robust Free-Text Rationale Evaluation","created":"2024-02-28","cited_by_count":4,"area":null},{"id":"2407.13594","title":"Validating Mechanistic Interpretations: An Axiomatic Approach","created":"2024-07-18","cited_by_count":4,"area":"mechinterp"},{"id":"2502.12992","title":"B-cos LM: Efficiently Transforming Pre-trained Language Models for Improved Explainability","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2504.01137","title":"Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models","created":"2025-04-01","cited_by_count":4,"area":null},{"id":"2109.09202","title":"Automated and Explainable Ontology Extension Based on Deep Learning: A Case Study in the Chemical Domain","created":"2021-09-19","cited_by_count":3,"area":null},{"id":"2210.07469","title":"StyLEx: Explaining Style Using Human Lexical Annotations","created":"2022-10-14","cited_by_count":3,"area":null},{"id":"2306.11260","title":"A Novel Counterfactual Data Augmentation Method for Aspect-Based Sentiment Analysis","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2307.09050","title":"R-Cut: Enhancing Explainability in Vision Transformers with Relationship Weighted Out and Cut","created":"2023-07-18","cited_by_count":3,"area":null},{"id":"2103.14919","title":"You Can Do Better! If You Elaborate the Reason When Making Prediction","created":"2021-03-27","cited_by_count":2,"area":null},{"id":"2104.07894","title":"Faithful and Plausible Explanations of Medical Code Predictions","created":"2021-04-16","cited_by_count":2,"area":null},{"id":"2306.05143","title":"Genomic Interpreter: A Hierarchical Genomic Deep Neural Network with 1D Shifted Window Transformer","created":"2023-06-08","cited_by_count":2,"area":null},{"id":"2310.06977","title":"Why bother with geometry? On the relevance of linear decompositions of Transformer embeddings","created":"2023-10-10","cited_by_count":2,"area":null},{"id":"2310.18496","title":"How Well Do Feature-Additive Explainers Explain Feature-Additive Predictors?","created":"2023-10-27","cited_by_count":2,"area":null},{"id":"2409.05208","title":"Influence-based Attributions can be Manipulated","created":"2024-09-08","cited_by_count":2,"area":null},{"id":"2108.10692","title":"Generalized Optimal Linear Orders","created":"2021-08-13","cited_by_count":1,"area":null},{"id":"2201.13230","title":"POTATO: exPlainable infOrmation exTrAcTion framewOrk","created":"2022-01-31","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":"2310.13610","title":"Make Your Decision Convincing! A Unified Two-Stage Framework: Self-Attribution and Decision-Making","created":"2023-10-20","cited_by_count":1,"area":null},{"id":"2402.08155","title":"CMA-R:Causal Mediation Analysis for Explaining Rumour Detection","created":"2024-02-13","cited_by_count":1,"area":null},{"id":"2404.13645","title":"PEACH: Pretrained-embedding Explanation Across Contextual and Hierarchical Structure","created":"2024-04-21","cited_by_count":1,"area":null},{"id":"2407.16693","title":"Explanation Regularisation through the Lens of Attributions","created":"2024-07-23","cited_by_count":1,"area":null},{"id":"2407.21041","title":"They Look Like Each Other: Case-based Reasoning for Explainable Depression Detection on Twitter using Large Language Models","created":"2024-07-21","cited_by_count":1,"area":null},{"id":"2501.12775","title":"Regularization, Semi-supervision, and Supervision for a Plausible Attention-Based Explanation","created":"2025-01-22","cited_by_count":1,"area":null},{"id":"2601.10073","title":"ReaMIL: Reasoning- and Evidence-Aware Multiple Instance Learning for Whole-Slide Histopathology","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2605.12575","title":"Are Compact Rationales Free? Measuring Tile Selection Headroom in Frozen WSI-MIL","created":"2026-05-12","cited_by_count":1,"area":null}],"next_cursor":"100"}