{"total":16,"rows":[{"id":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"area":null},{"id":"2503.10728","title":"DarkBench: Benchmarking Dark Patterns in Large Language Models","created":"2025-03-13","cited_by_count":28,"area":null},{"id":"2410.12284","title":"Fool Me Once? Contrasting Textual and Visual Explanations in a Clinical Decision-Support Setting","created":"2024-10-16","cited_by_count":5,"area":null},{"id":"2410.16574","title":"How Can We Diagnose and Treat Bias in Large Language Models for Clinical Decision-Making?","created":"2024-10-21","cited_by_count":4,"area":null},{"id":"2603.14643","title":"Argumentation for Explainable and Globally Contestable Decision Support with LLMs","created":"2026-03-15","cited_by_count":3,"area":null},{"id":"2605.25052","title":"Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth","created":"2026-05-24","cited_by_count":3,"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":"2511.01706","title":"Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement","created":"2025-11-03","cited_by_count":1,"area":null},{"id":"2512.06814","title":"CAuSE: Decoding Multimodal Classifiers using Faithful Natural Language Explanation","created":"2025-12-07","cited_by_count":1,"area":null},{"id":"2503.08815","title":"Cross-Examiner: Evaluating Consistency of Large Language Model-Generated Explanations","created":"2025-03-11","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":"2603.18752","title":"WeNLEX: Weakly Supervised Natural Language Explanations for Multilabel Chest X-ray Classification","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2604.14325","title":"Faithfulness Serum: Mitigating the Faithfulness Gap in Textual Explanations of LLM Decisions via Attribution Guidance","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2607.21090","title":"Training Large Language Models for Self-Explanation Faithfulness","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2609.22553","title":"Correct Diagnosis, Better Feedback: A Symbolic-Verifier for Faithful LLM Tutoring Feedback in Logic Proofs","created":"2026-09-18","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}