{"total":101,"rows":[{"id":"2303.02536","title":"Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations","created":"2023-03-05","cited_by_count":209,"area":null},{"id":"2306.01941","title":"AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap","created":"2023-06-02","cited_by_count":123,"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":"2409.05746","title":"LLMs Will Always Hallucinate, and We Need to Live With This","created":"2024-09-09","cited_by_count":78,"area":null},{"id":"2406.11289","title":"A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models","created":"2024-06-17","cited_by_count":52,"area":null},{"id":"2310.00603","title":"Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals","created":"2023-10-01","cited_by_count":44,"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":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2407.10747","title":"Codebook LLMs: Evaluating LLMs as Measurement Tools for Political Science Concepts","created":"2024-07-15","cited_by_count":30,"area":null},{"id":"2310.03686","title":"DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers","created":"2023-10-05","cited_by_count":22,"area":null},{"id":"2310.19660","title":"Interpretable-by-Design Text Understanding with Iteratively Generated Concept Bottleneck","created":"2023-10-30","cited_by_count":22,"area":null},{"id":"2404.09554","title":"Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda","created":"2024-04-15","cited_by_count":22,"area":null},{"id":"2305.13214","title":"Atomic Inference for NLI with Generated Facts as Atoms","created":"2023-05-22","cited_by_count":18,"area":null},{"id":"2410.02970","title":"F-Fidelity: A Robust Framework for Faithfulness Evaluation of Explainable AI","created":"2024-10-03","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":"2505.24858","title":"MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs","created":"2025-05-30","cited_by_count":16,"area":null},{"id":"2305.14250","title":"Language Models with Rationality","created":"2023-05-23","cited_by_count":15,"area":null},{"id":"2305.14582","title":"Interpretation of Time-Series Deep Models: A Survey","created":"2023-05-23","cited_by_count":15,"area":null},{"id":"2307.05902","title":"Stability Guarantees for Feature Attributions with Multiplicative Smoothing","created":"2023-07-12","cited_by_count":14,"area":null},{"id":"2404.12545","title":"Latent Concept-based Explanation of NLP Models","created":"2024-04-18","cited_by_count":13,"area":null},{"id":"2503.01623","title":"Lost in Moderation: How Commercial Content Moderation APIs Over- and Under-Moderate Group-Targeted Hate Speech and Linguistic Variations","created":"2025-03-03","cited_by_count":13,"area":null},{"id":"2311.17983","title":"Improving Interpretation Faithfulness for Vision Transformers","created":"2023-11-29","cited_by_count":12,"area":null},{"id":"2406.08958","title":"An Unsupervised Approach to Achieve Supervised-Level Explainability in Healthcare Records","created":"2024-06-13","cited_by_count":12,"area":null},{"id":"2502.18848","title":"A Causal Lens for Evaluating Faithfulness Metrics","created":"2025-02-26","cited_by_count":12,"area":null},{"id":"2405.05386","title":"Interpretability Needs a New Paradigm","created":"2024-05-08","cited_by_count":11,"area":null},{"id":"2408.08137","title":"Normalized AOPC: Fixing Misleading Faithfulness Metrics for Feature Attribution Explainability","created":"2024-08-15","cited_by_count":10,"area":null},{"id":"2504.06227","title":"LExT: Towards Evaluating Trustworthiness of Natural Language Explanations","created":"2025-04-08","cited_by_count":9,"area":null},{"id":"2504.13787","title":"Probabilistic Stability Guarantees for Feature Attributions","created":"2025-04-18","cited_by_count":9,"area":null},{"id":"2507.10583","title":"$\\texttt{Droid}$: A Resource Suite for AI-Generated Code Detection","created":"2025-07-11","cited_by_count":9,"area":null},{"id":"2405.19433","title":"Beyond Agreement: Diagnosing the Rationale Alignment of Automated Essay Scoring Methods based on Linguistically-informed Counterfactuals","created":"2024-05-29","cited_by_count":8,"area":null},{"id":"2502.11100","title":"Towards Achieving Concept Completeness for Textual Concept Bottleneck Models","created":"2025-02-16","cited_by_count":7,"area":null},{"id":"2310.16316","title":"Sum-of-Parts: Self-Attributing Neural Networks with End-to-End Learning of Feature Groups","created":"2023-10-25","cited_by_count":6,"area":null},{"id":"2404.04728","title":"Navigating the Landscape of Hint Generation Research: From the Past to the Future","created":"2024-04-06","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":"2406.19170","title":"The Illusion of Competence: Evaluating the Effect of Explanations on Users' Mental Models of Visual Question Answering Systems","created":"2024-06-27","cited_by_count":6,"area":null},{"id":"2311.07497","title":"Multilingual Nonce Dependency Treebanks: Understanding how Language Models represent and process syntactic structure","created":"2023-11-13","cited_by_count":5,"area":null},{"id":"2411.16760","title":"LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions","created":"2024-11-24","cited_by_count":5,"area":null},{"id":"2505.17630","title":"Correcting Gradient-Based Circuit Localization via Interaction-Aware Backpropagation","created":"2025-05-23","cited_by_count":5,"area":null},{"id":"2402.03043","title":"SIDU-TXT: An XAI Algorithm for NLP with a Holistic Assessment Approach","created":"2024-02-05","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":"2404.02619","title":"Adjusting Interpretable Dimensions in Embedding Space with Human Judgments","created":"2024-04-03","cited_by_count":4,"area":null},{"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":"2502.16395","title":"AIRepr: An Analyst-Inspector Framework for Evaluating Reproducibility of LLMs in Data Science","created":"2025-02-23","cited_by_count":4,"area":null},{"id":"2505.21657","title":"Explaining Large Language Models with gSMILE","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2510.05362","title":"Residualized Similarity for Faithfully Explainable Authorship Verification","created":"2025-10-06","cited_by_count":4,"area":null},{"id":"2305.09400","title":"Consistent Multi-Granular Rationale Extraction for Explainable Multi-hop Fact Verification","created":"2023-05-16","cited_by_count":3,"area":null},{"id":"2406.15265","title":"Perception of Phonological Assimilation by Neural Speech Recognition Models","created":"2024-06-21","cited_by_count":3,"area":null},{"id":"2410.01482","title":"One Wave To Explain Them All: A Unifying Perspective On Feature Attribution","created":"2024-10-02","cited_by_count":3,"area":null},{"id":"2410.05085","title":"Explanation sensitivity to the randomness of large language models: the case of journalistic text classification","created":"2024-10-07","cited_by_count":3,"area":null},{"id":"2410.06950","title":"Faithful Interpretation for Graph Neural Networks","created":"2024-10-09","cited_by_count":3,"area":null},{"id":"2412.12318","title":"Graph-Guided Textual Explanation Generation Framework","created":"2024-12-16","cited_by_count":3,"area":null},{"id":"2505.01198","title":"Gender Bias in Explainability: Investigating Performance Disparity in Post-hoc Methods","created":"2025-05-02","cited_by_count":3,"area":null},{"id":"2505.19299","title":"A Necessary Step toward Faithfulness: Measuring and Improving Consistency in Free-Text Explanations","created":"2025-05-25","cited_by_count":3,"area":null},{"id":"2508.06374","title":"Evaluating Style-Personalized Text Generation: Challenges and Directions","created":"2025-08-08","cited_by_count":3,"area":null},{"id":"2304.06337","title":"Computational modeling of semantic change","created":"2023-04-13","cited_by_count":2,"area":null},{"id":"2311.09558","title":"What if you said that differently?: How Explanation Formats Affect Human Feedback Efficacy and User Perception","created":"2023-11-16","cited_by_count":2,"area":null},{"id":"2409.07423","title":"Enhancing adversarial robustness in Natural Language Inference using explanations","created":"2024-09-11","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":"2501.02891","title":"Explaining Humour Style Classifications: An XAI Approach to Understanding Computational Humour Analysis","created":"2025-01-06","cited_by_count":2,"area":null},{"id":"2501.03182","title":"Boosting Explainability through Selective Rationalization in Pre-trained Language Models","created":"2025-01-03","cited_by_count":2,"area":null},{"id":"2506.19113","title":"Argument-Based Consistency in Toxicity Explanations of LLMs","created":"2025-06-23","cited_by_count":2,"area":null},{"id":"2508.07636","title":"Attribution Explanations for Deep Neural Networks: A Theoretical Perspective","created":"2025-08-11","cited_by_count":2,"area":null},{"id":"2601.10700","title":"LIBERTy: A Causal Framework for Benchmarking Concept-Based Explanations of LLMs with Structural Counterfactuals","created":"2026-01-15","cited_by_count":2,"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":"2408.00166","title":"Review of Explainable Graph-Based Recommender Systems","created":"2024-07-31","cited_by_count":1,"area":null},{"id":"2410.03964","title":"Variational Language Concepts for Interpreting Foundation Language Models","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2412.20798","title":"Reconciling Privacy and Explainability in High-Stakes: A Systematic Inquiry","created":"2024-12-30","cited_by_count":1,"area":null},{"id":"2502.15261","title":"Corrections Meet Explanations: A Unified Framework for Explainable Grammatical Error Correction","created":"2025-02-21","cited_by_count":1,"area":null},{"id":"2507.10585","title":"A Taxonomy for Design and Evaluation of Prompt-Based Natural Language Explanations","created":"2025-07-11","cited_by_count":1,"area":null},{"id":"2508.05003","title":"A Multi-Stage Large Language Model Framework for Extracting Suicide-Related Social Determinants of Health","created":"2025-08-07","cited_by_count":1,"area":null},{"id":"2510.13393","title":"Learnable Game-theoretic Policy Optimization for Data-centric Self-explanation Rationalization","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2510.16233","title":"Machine Learning for Climate Policy: Understanding Policy Progression in the European Green Deal","created":"2025-10-17","cited_by_count":1,"area":null},{"id":"2510.21884","title":"Support-Contra Asymmetry in LLM Explanations","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2601.01446","title":"iFlip: Iterative Feedback-driven Counterfactual Example Refinement","created":"2026-01-04","cited_by_count":1,"area":null},{"id":"2602.00300","title":"Faithful-Patchscopes: Understanding and Mitigating Model Bias in Hidden Representations Explanation of Large Language Models","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2604.12069","title":"Robust Explanations for User Trust in Enterprise NLP Systems","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2604.21092","title":"Mind the Prompt: Self-adaptive Generation of Task Plan Explanations via LLMs","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2607.06648","title":"Final Checkpoints Are Not Enough: Analyzing Latent Reasoning Faithfulness Along Training Trajectories","created":"2026-07-07","cited_by_count":1,"area":null},{"id":"2403.05581","title":"Can Interpretability Layouts Influence Human Perception of Offensive Sentences?","created":"2024-03-01","cited_by_count":0,"area":null},{"id":"2409.13291","title":"Localized Gaussians as Self-Attention Weights for Point Clouds Correspondence","created":"2024-09-20","cited_by_count":0,"area":null},{"id":"2506.09277","title":"NeuroFaith: Evaluating LLM Self-Explanation Faithfulness via Internal Representation Alignment","created":"2025-06-10","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":"2508.01486","title":"Human-Centered Supervision for Sentiment Analysis in Telugu: A Systematic Inquiry Beyond Accuracy","created":"2025-08-02","cited_by_count":0,"area":null},{"id":"2508.10482","title":"When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in the Context of Natural Language Processing","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2509.22291","title":"Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection?","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2510.02629","title":"Evaluation Framework for Highlight Explanations of Context Utilisation in Language Models","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2512.11108","title":"Explanation Bias is a Product: Revealing the Hidden Lexical and Position Preferences in Post-Hoc Feature Attribution","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2512.14719","title":"Hybrid Attribution Priors for Explainable and Robust Model Training","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2512.20328","title":"Toward Explaining Large Language Models in Software Engineering Tasks","created":"2025-12-23","cited_by_count":0,"area":null},{"id":"2603.08241","title":"Sensivity of LLMs' Explanations to the Training Randomness:Context, Class & Task Dependencies","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2603.13163","title":"Towards Faithful Multimodal Concept Bottleneck Models","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2603.19460","title":"GeoLAN: Geometric Learning of Latent Explanatory Directions in Large Language Models","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2605.10988","title":"Seeing the Needle in the Haystack: Towards Weakly-Supervised Log Instance Anomaly Localization via Counterfactual Perturbation","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2606.12210","title":"Can News Predict the Market? Limits of Zero-Shot Financial NLP and the Role of Explainable AI","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2607.13260","title":"Discourse-Aware Policy Analysis with Argumentation: A Hybrid LLM-Symbolic Framework for Disaster Governance","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.15241","title":"Beyond the Leaderboard: Design Lessons for Trustworthy Multimodal VQA","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.15957","title":"From Plausible to Actionable: A Position on LLM Self-Explanations","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2608.25028","title":"Behind the [MASK]: Disentangling Representation and Faithfulness in DAPF-Based Dementia Detection","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.03330","title":"Less Is Moral: A CHARMing Framework for Moral Foundations Detection in Endorsement Behaviour","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.32230","title":"\"Where Can I Trust You?\": Boundary-Aware Evaluation of Surrogate Fidelity","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":"100"}