{"total":85,"rows":[{"id":"2505.05410","title":"Reasoning Models Don't Always Say What They Think","created":"2025-05-08","cited_by_count":415,"area":"lr"},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202,"area":null},{"id":"2503.08679","title":"Chain-of-Thought Reasoning In The Wild Is Not Always Faithful","created":"2025-03-11","cited_by_count":170,"area":"lr"},{"id":"2402.01761","title":"Rethinking Interpretability in the Era of Large Language Models","created":"2024-01-30","cited_by_count":111,"area":"lr"},{"id":"2401.07927","title":"Are self-explanations from Large Language Models faithful?","created":"2024-01-15","cited_by_count":101,"area":null},{"id":"2310.11207","title":"Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations","created":"2023-10-17","cited_by_count":90,"area":"lr"},{"id":"2310.08559","title":"Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement","created":"2023-10-12","cited_by_count":89,"area":"lr"},{"id":"2501.08156","title":"Are DeepSeek R1 And Other Reasoning Models More Faithful?","created":"2025-01-14","cited_by_count":72,"area":"lr"},{"id":"2506.13206","title":"Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models","created":"2025-06-16","cited_by_count":65,"area":"lr"},{"id":"2408.05109","title":"A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?","created":"2024-08-09","cited_by_count":56,"area":null},{"id":"2502.14829","title":"Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps","created":"2025-02-20","cited_by_count":47,"area":"lr"},{"id":"2406.07882","title":"Designing a Dashboard for Transparency and Control of Conversational AI","created":"2024-06-12","cited_by_count":46,"area":null},{"id":"2403.05518","title":"Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought","created":"2024-03-08","cited_by_count":39,"area":"lr"},{"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":"2401.13986","title":"Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning","created":"2024-01-25","cited_by_count":26,"area":null},{"id":"2403.09606","title":"Large Language Models and Causal Inference in Collaboration: A Survey","created":"2024-03-14","cited_by_count":26,"area":null},{"id":"2410.15319","title":"Causality for Large Language Models","created":"2024-10-20","cited_by_count":25,"area":null},{"id":"2412.06771","title":"Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertainty","created":"2024-12-09","cited_by_count":25,"area":null},{"id":"2406.19354","title":"Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs?","created":"2024-06-27","cited_by_count":24,"area":null},{"id":"2505.16467","title":"Reading Between the Prompts: How Stereotypes Shape LLM's Implicit Personalization","created":"2025-05-22","cited_by_count":24,"area":null},{"id":"2505.13774","title":"Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models","created":"2025-05-19","cited_by_count":23,"area":"lr"},{"id":"2311.08576","title":"Towards Evaluating AI Systems for Moral Status Using Self-Reports","created":"2023-11-14","cited_by_count":22,"area":null},{"id":"2506.22777","title":"Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning","created":"2025-06-28","cited_by_count":21,"area":"lr"},{"id":"2402.04678","title":"FaithLM: Towards Faithful Explanations for Large Language Models","created":"2024-02-07","cited_by_count":19,"area":null},{"id":"2403.01152","title":"A Survey of AI-generated Text Forensic Systems: Detection, Attribution, and Characterization","created":"2024-03-02","cited_by_count":19,"area":null},{"id":"2408.16482","title":"Self-Alignment: Improving Alignment of Cultural Values in LLMs via In-Context Learning","created":"2024-08-29","cited_by_count":19,"area":"alignment"},{"id":"2412.12386","title":"Interpretable LLM-based Table Question Answering","created":"2024-12-16","cited_by_count":18,"area":null},{"id":"2412.18004","title":"Correctness is not Faithfulness in RAG Attributions","created":"2024-12-23","cited_by_count":18,"area":null},{"id":"2406.19482","title":"xTower: A Multilingual LLM for Explaining and Correcting Translation Errors","created":"2024-06-27","cited_by_count":17,"area":null},{"id":"2602.20710","title":"Counterfactual Simulation Training for Chain-of-Thought Faithfulness","created":"2026-02-24","cited_by_count":17,"area":"lr"},{"id":"2509.09396","title":"LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations","created":"2025-09-11","cited_by_count":16,"area":"synth"},{"id":"2602.02905","title":"FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific Insights","created":"2026-02-02","cited_by_count":16,"area":"agents"},{"id":"2412.14140","title":"GLIDER: Grading LLM Interactions and Decisions using Explainable Ranking","created":"2024-12-18","cited_by_count":14,"area":null},{"id":"2602.02639","title":"A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior","created":"2026-02-02","cited_by_count":13,"area":"lr"},{"id":"2310.13439","title":"Self-Consistency of Large Language Models under Ambiguity","created":"2023-10-20","cited_by_count":12,"area":"lr"},{"id":"2407.00219","title":"Evaluating Human Alignment and Model Faithfulness of LLM Rationale","created":"2024-06-28","cited_by_count":12,"area":null},{"id":"2505.23945","title":"A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models","created":"2025-05-29","cited_by_count":12,"area":"lr"},{"id":"2312.12747","title":"ALMANACS: A Simulatability Benchmark for Language Model Explainability","created":"2023-12-20","cited_by_count":11,"area":null},{"id":"2405.05386","title":"Interpretability Needs a New Paradigm","created":"2024-05-08","cited_by_count":11,"area":null},{"id":"2502.19573","title":"Do Large Language Models Know How Much They Know?","created":"2025-02-26","cited_by_count":11,"area":null},{"id":"2505.17406","title":"Robust Answers, Fragile Logic: Probing the Decoupling Hypothesis in LLM Reasoning","created":"2025-05-23","cited_by_count":11,"area":"lr"},{"id":"2502.18156","title":"Can LLMs Explain Themselves Counterfactually?","created":"2025-02-25","cited_by_count":10,"area":null},{"id":"2406.02018","title":"Why Would You Suggest That? Human Trust in Language Model Responses","created":"2024-06-04","cited_by_count":9,"area":null},{"id":"2501.05855","title":"ConSim: Measuring Concept-Based Explanations' Effectiveness with Automated Simulatability","created":"2025-01-10","cited_by_count":9,"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":"2505.21740","title":"Counterfactual Simulatability of LLM Explanations for Generation Tasks","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2309.11439","title":"Controlled Generation with Prompt Insertion for Natural Language Explanations in Grammatical Error Correction","created":"2023-09-20","cited_by_count":7,"area":null},{"id":"2505.16477","title":"Advancing the Scientific Method with Large Language Models: From Hypothesis to Discovery","created":"2025-05-22","cited_by_count":7,"area":null},{"id":"2601.03775","title":"Do LLM Self-Explanations Help Users Predict Model Behavior? Evaluating Counterfactual Simulatability with Pragmatic Perturbations","created":"2026-01-07","cited_by_count":7,"area":null},{"id":"2604.22074","title":"Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning","created":"2026-04-23","cited_by_count":7,"area":"lr"},{"id":"2311.08390","title":"Predicting Text Preference Via Structured Comparative Reasoning","created":"2023-11-14","cited_by_count":6,"area":"lr"},{"id":"2409.14306","title":"LLMs are One-Shot URL Classifiers and Explainers","created":"2024-09-22","cited_by_count":6,"area":null},{"id":"2410.13073","title":"PromptExp: Multi-granularity Prompt Explanation of Large Language Models","created":"2024-10-16","cited_by_count":6,"area":null},{"id":"2410.20811","title":"Bridging the Gap between Expert and Language Models: Concept-guided Chess Commentary Generation and Evaluation","created":"2024-10-28","cited_by_count":6,"area":null},{"id":"2510.13272","title":"Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation","created":"2025-10-15","cited_by_count":6,"area":"lr"},{"id":"2406.15085","title":"Evaluating Input Feature Explanations through a Unified Diagnostic Evaluation Framework","created":"2024-06-21","cited_by_count":5,"area":null},{"id":"2311.07099","title":"Explanation-aware Soft Ensemble Empowers Large Language Model In-context Learning","created":"2023-11-13","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":"2407.12999","title":"Securing the Future of GenAI: Policy and Technology","created":"2024-05-21","cited_by_count":4,"area":null},{"id":"2410.14180","title":"XForecast: Evaluating Natural Language Explanations for Time Series Forecasting","created":"2024-10-18","cited_by_count":4,"area":null},{"id":"2509.21631","title":"Towards Transparent AI: A Survey on Explainable Language Models","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2510.01048","title":"Interpreting Language Models Through Concept Descriptions: A Survey","created":"2025-10-01","cited_by_count":3,"area":"mechinterp"},{"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":"2511.09373","title":"Routesplain: Towards Faithful and Intervenable Routing for Software-related Tasks","created":"2025-11-12","cited_by_count":2,"area":null},{"id":"2608.16747","title":"Would this change your answer? Evaluating Explanations of LLM Behavior In The Wild with Counterfactual Experiments","created":"2026-08-17","cited_by_count":2,"area":"lr"},{"id":"2508.18467","title":"The AI in the Mirror: LLM Self-Recognition in an Iterated Public Goods Game","created":"2025-08-25","cited_by_count":1,"area":null},{"id":"2509.22363","title":"Investigating Faithfulness in Large Audio Language Models","created":"2025-09-26","cited_by_count":1,"area":"lr"},{"id":"2510.21884","title":"Support-Contra Asymmetry in LLM Explanations","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2512.07564","title":"Toward More Reliable Artificial Intelligence: Reducing Hallucinations in Vision-Language Models","created":"2025-12-08","cited_by_count":1,"area":"mllm"},{"id":"2602.06841","title":"From Features to Actions: Explainability in Traditional and Agentic AI Systems","created":"2026-02-06","cited_by_count":1,"area":"agents"},{"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":"2605.21102","title":"ACL-Verbatim: hallucination-free question answering for research","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2606.01148","title":"Not All Explanations Simulate Equally: Comparing Verbalized Feature Attributions and Self-Generated Rationales","created":"2026-05-31","cited_by_count":1,"area":"synth"},{"id":"2412.11536","title":"Let your LLM generate a few tokens and you will reduce the need for retrieval","created":"2024-12-16","cited_by_count":0,"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":"2601.13122","title":"Responsible AI for General-Purpose Systems: Overview, Challenges, and A Path Forward","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2604.04418","title":"Justified or Just Convincing? Error Verifiability as a Dimension of LLM Quality","created":"2026-04-06","cited_by_count":0,"area":"lr"},{"id":"2606.15779","title":"Faithful Action-unit Causal Reasoning for Counterfactually Faithful Emotion Explanations","created":"2026-06-14","cited_by_count":0,"area":"lr"},{"id":"2607.09306","title":"Exposure is not manifestation: measurement target and output resolution jointly determine which behavioural-faithfulness evaluator wins","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2608.02238","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2609.08585","title":"Limitations of Automated Simulatability: LLM Simulators Can Bypass Explanations","created":"2026-09-08","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},{"id":"2610.00314","title":"Predictive Credit: Measuring What Scientific Explanations Add to Experimental Forecasts","created":"2026-09-29","cited_by_count":0,"area":"agents"}],"next_cursor":null}