{"total":75,"rows":[{"id":"2212.07919","title":"ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning","created":"2022-12-15","cited_by_count":177,"area":"lr"},{"id":"2205.11822","title":"Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations","created":"2022-05-24","cited_by_count":159,"area":"lr"},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2305.18029","title":"Faithfulness Tests for Natural Language Explanations","created":"2023-05-29","cited_by_count":107,"area":null},{"id":"2202.10419","title":"Interpreting Language Models with Contrastive Explanations","created":"2022-02-21","cited_by_count":92,"area":null},{"id":"2307.08678","title":"Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations","created":"2023-07-17","cited_by_count":85,"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":"2105.06965","title":"Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction","created":"2021-05-14","cited_by_count":59,"area":null},{"id":"2207.04153","title":"Probing Classifiers are Unreliable for Concept Removal and Detection","created":"2022-07-08","cited_by_count":41,"area":null},{"id":"2404.00225","title":"Heterogeneous Contrastive Learning for Foundation Models and Beyond","created":"2024-03-30","cited_by_count":27,"area":null},{"id":"2103.13701","title":"ECINN: Efficient Counterfactuals from Invertible Neural Networks","created":"2021-03-25","cited_by_count":26,"area":null},{"id":"2501.17546","title":"Is Conversational XAI All You Need? Human-AI Decision Making With a Conversational XAI Assistant","created":"2025-01-29","cited_by_count":26,"area":null},{"id":"2307.15054","title":"A Geometric Notion of Causal Probing","created":"2023-07-27","cited_by_count":25,"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":"2508.21456","title":"Morae: Proactively Pausing UI Agents for User Choices","created":"2025-08-29","cited_by_count":19,"area":null},{"id":"2110.00527","title":"Consistent Explanations by Contrastive Learning","created":"2021-10-01","cited_by_count":18,"area":null},{"id":"2312.01279","title":"TextGenSHAP: Scalable Post-hoc Explanations in Text Generation with Long Documents","created":"2023-12-03","cited_by_count":17,"area":"lr"},{"id":"2410.04253","title":"Contrastive Explanations That Anticipate Human Misconceptions Can Improve Human Decision-Making Skills","created":"2024-10-05","cited_by_count":14,"area":null},{"id":"2206.11083","title":"Investigating the Benefits of Free-Form Rationales","created":"2022-05-25","cited_by_count":13,"area":null},{"id":"2512.18792","title":"The Dead Salmons of AI Interpretability","created":"2025-12-21","cited_by_count":12,"area":null},{"id":"2305.07378","title":"Surfacing Biases in Large Language Models using Contrastive Input Decoding","created":"2023-05-12","cited_by_count":11,"area":null},{"id":"2310.11906","title":"Rather a Nurse than a Physician -- Contrastive Explanations under Investigation","created":"2023-10-18","cited_by_count":11,"area":null},{"id":"2506.05451","title":"Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety","created":"2025-06-05","cited_by_count":10,"area":"safety"},{"id":"2109.07983","title":"Let the CAT out of the bag: Contrastive Attributed explanations for Text","created":"2021-09-16","cited_by_count":9,"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":"2210.12673","title":"Lexical Generalization Improves with Larger Models and Longer Training","created":"2022-10-23","cited_by_count":9,"area":null},{"id":"2210.13575","title":"Does Self-Rationalization Improve Robustness to Spurious Correlations?","created":"2022-10-24","cited_by_count":9,"area":null},{"id":"2104.08735","title":"Learning with Instance Bundles for Reading Comprehension","created":"2021-04-18","cited_by_count":8,"area":null},{"id":"2210.00107","title":"Contrastive Corpus Attribution for Explaining Representations","created":"2022-09-30","cited_by_count":7,"area":null},{"id":"2309.07733","title":"Explaining Speech Classification Models via Word-Level Audio Segments and Paralinguistic Features","created":"2023-09-14","cited_by_count":7,"area":null},{"id":"2305.08135","title":"Distinguish Before Answer: Generating Contrastive Explanation as Knowledge for Commonsense Question Answering","created":"2023-05-14","cited_by_count":6,"area":null},{"id":"2305.08208","title":"Learning to Generalize for Cross-domain QA","created":"2023-05-14","cited_by_count":6,"area":null},{"id":"2404.07498","title":"Interactive Prompt Debugging with Sequence Salience","created":"2024-04-11","cited_by_count":6,"area":null},{"id":"2405.11891","title":"Unveiling and Manipulating Prompt Influence in Large Language Models","created":"2024-05-20","cited_by_count":6,"area":null},{"id":"2311.08614","title":"XplainLLM: A Knowledge-Augmented Dataset for Reliable Grounded Explanations in LLMs","created":"2023-11-15","cited_by_count":5,"area":"lr"},{"id":"2312.13616","title":"Navigating the Structured What-If Spaces: Counterfactual Generation via Structured Diffusion","created":"2023-12-21","cited_by_count":5,"area":"diffusion"},{"id":"2404.01361","title":"LLM Attributor: Interactive Visual Attribution for LLM Generation","created":"2024-04-01","cited_by_count":5,"area":null},{"id":"2411.02643","title":"A Comparative Analysis of Counterfactual Explanation Methods for Text Classifiers","created":"2024-11-04","cited_by_count":5,"area":null},{"id":"2206.02790","title":"Improving Model Understanding and Trust with Counterfactual Explanations of Model Confidence","created":"2022-06-06","cited_by_count":4,"area":null},{"id":"2301.05163","title":"Signed Directed Graph Contrastive Learning with Laplacian Augmentation","created":"2023-01-12","cited_by_count":4,"area":null},{"id":"2303.05729","title":"Explaining Model Confidence Using Counterfactuals","created":"2023-03-10","cited_by_count":4,"area":null},{"id":"2306.06339","title":"Two-Stage Holistic and Contrastive Explanation of Image Classification","created":"2023-06-10","cited_by_count":4,"area":null},{"id":"2310.13499","title":"DistillCSE: Distilled Contrastive Learning for Sentence Embeddings","created":"2023-10-20","cited_by_count":4,"area":"distill"},{"id":"2312.06499","title":"TaCo: Targeted Concept Erasure Prevents Non-Linear Classifiers From Detecting Protected Attributes","created":"2023-12-11","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":"2103.14973","title":"Explaining the Road Not Taken","created":"2021-03-27","cited_by_count":3,"area":null},{"id":"2402.09947","title":"Explaining Probabilistic Models with Distributional Values","created":"2024-02-15","cited_by_count":3,"area":null},{"id":"2404.18831","title":"ConPro: Learning Severity Representation for Medical Images using Contrastive Learning and Preference Optimization","created":"2024-04-29","cited_by_count":3,"area":null},{"id":"2509.26543","title":"The Unheard Alternative: Contrastive Explanations for Speech-to-Text Models","created":"2025-09-30","cited_by_count":3,"area":null},{"id":"2207.06269","title":"Policy Optimization with Sparse Global Contrastive Explanations","created":"2022-07-13","cited_by_count":2,"area":null},{"id":"2211.00369","title":"A General Search-based Framework for Generating Textual Counterfactual Explanations","created":"2022-11-01","cited_by_count":2,"area":null},{"id":"2211.05987","title":"CCPrefix: Counterfactual Contrastive Prefix-Tuning for Many-Class Classification","created":"2022-11-11","cited_by_count":2,"area":null},{"id":"2504.03744","title":"Comparative Explanations: Explanation Guided Decision Making for Human-in-the-Loop Preference Selection","created":"2025-04-01","cited_by_count":2,"area":null},{"id":"2602.18160","title":"Unifying Formal Explanations: A Complexity-Theoretic Perspective","created":"2026-02-20","cited_by_count":2,"area":null},{"id":"2210.10012","title":"Log-linear Guardedness and its Implications","created":"2022-10-18","cited_by_count":1,"area":null},{"id":"2307.00680","title":"CLIMAX: An exploration of Classifier-Based Contrastive Explanations","created":"2023-07-02","cited_by_count":1,"area":null},{"id":"2312.16291","title":"Observable Propagation: Uncovering Feature Vectors in Transformers","created":"2023-12-26","cited_by_count":1,"area":"mechinterp"},{"id":"2210.08902","title":"Beyond Model Interpretability: On the Faithfulness and Adversarial Robustness of Contrastive Textual Explanations","created":"2022-10-17","cited_by_count":0,"area":null},{"id":"2212.07126","title":"Explainability of Text Processing and Retrieval Methods: A Survey","created":"2022-12-14","cited_by_count":0,"area":null},{"id":"2305.18915","title":"Empirical Sufficiency Lower Bounds for Language Modeling with Locally-Bootstrapped Semantic Structures","created":"2023-05-30","cited_by_count":0,"area":"synth"},{"id":"2310.04856","title":"LIPEx-Locally Interpretable Probabilistic Explanations-To Look Beyond The True Class","created":"2023-10-07","cited_by_count":0,"area":null},{"id":"2310.11363","title":"Disentangling the Linguistic Competence of Privacy-Preserving BERT","created":"2023-10-17","cited_by_count":0,"area":null},{"id":"2403.07486","title":"XpertAI: uncovering regression model strategies for sub-manifolds","created":"2024-03-12","cited_by_count":0,"area":null},{"id":"2403.15492","title":"Visual Analytics for Fine-grained Text Classification Models and Datasets","created":"2024-03-21","cited_by_count":0,"area":null},{"id":"2406.11785","title":"CELL your Model: Contrastive Explanations for Large Language Models","created":"2024-06-17","cited_by_count":0,"area":null},{"id":"2503.01914","title":"Conceptual Contrastive Edits in Textual and Vision-Language Retrieval","created":"2025-03-01","cited_by_count":0,"area":null},{"id":"2505.17832","title":"Emerging categories in scientific explanations","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2507.21302","title":"Can human clinical rationales improve the performance and explainability of clinical text classification models?","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2510.11079","title":"Argumentation-Based Explainability for Legal AI: Comparative and Regulatory Perspectives","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2606.01482","title":"Beyond Topical Similarity: Contrastive Evidence Retrieval with Interpretable Attention Alignment in RAG","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2607.27904","title":"Contrastive Concept Importance: Explaining Pairwise Class Decisions Through Automatically Extracted Concept Representations","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.21662","title":"Why This, Not That? Mining User Profiles for Pair-wise Counterfactuals","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.00090","title":"Assessing Alignment and Stability of Feature Importance Explanations via Weight of Evidence","created":"2026-08-31","cited_by_count":0,"area":"lr"},{"id":"2609.02399","title":"Contrastive Explanations in Quantitative Bipolar Argumentation Frameworks","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.30151","title":"Does a model's stated reason for rejecting a candidate do any work?","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}