{"total":106,"rows":[{"id":"2402.05070","title":"A Roadmap to Pluralistic Alignment","created":"2024-02-07","cited_by_count":184,"area":"alignment"},{"id":"2402.00367","title":"Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration","created":"2024-02-01","cited_by_count":180,"area":null},{"id":"2407.18418","title":"Know Your Limits: A Survey of Abstention in Large Language Models","created":"2024-07-25","cited_by_count":121,"area":null},{"id":"2504.16828","title":"Process Reward Models That Think","created":"2025-04-23","cited_by_count":118,"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":"2401.13835","title":"What Large Language Models Know and What People Think They Know","created":"2024-01-24","cited_by_count":110,"area":"lr"},{"id":"2405.20974","title":"SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales","created":"2024-05-31","cited_by_count":105,"area":null},{"id":"2410.13788","title":"Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questions","created":"2024-10-17","cited_by_count":76,"area":null},{"id":"2403.05973","title":"Calibrating Large Language Models Using Their Generations Only","created":"2024-03-09","cited_by_count":65,"area":null},{"id":"2505.14489","title":"Reasoning Models Better Express Their Confidence","created":"2025-05-20","cited_by_count":65,"area":"lr"},{"id":"2404.10960","title":"Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations","created":"2024-04-16","cited_by_count":54,"area":null},{"id":"2408.15204","title":"Can Unconfident LLM Annotations Be Used for Confident Conclusions?","created":"2024-08-27","cited_by_count":49,"area":null},{"id":"2503.14477","title":"Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations","created":"2025-03-18","cited_by_count":48,"area":null},{"id":"2412.12472","title":"Knowledge Boundary of Large Language Models: A Survey","created":"2024-12-17","cited_by_count":40,"area":null},{"id":"2502.11028","title":"Mind the Confidence Gap: Overconfidence, Calibration, and Distractor Effects in Large Language Models","created":"2025-02-16","cited_by_count":40,"area":null},{"id":"2502.08554","title":"Fostering Appropriate Reliance on Large Language Models: The Role of Explanations, Sources, and Inconsistencies","created":"2025-02-12","cited_by_count":39,"area":null},{"id":"2403.12503","title":"Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices","created":"2024-03-19","cited_by_count":37,"area":null},{"id":"2410.20774","title":"Are LLM-Judges Robust to Expressions of Uncertainty? Investigating the effect of Epistemic Markers on LLM-based Evaluation","created":"2024-10-28","cited_by_count":29,"area":null},{"id":"2402.17124","title":"Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Models","created":"2024-02-27","cited_by_count":27,"area":null},{"id":"2510.26202","title":"What's In My Human Feedback? Learning Interpretable Descriptions of Preference Data","created":"2025-10-30","cited_by_count":26,"area":"alignment"},{"id":"2407.19200","title":"On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs","created":"2024-07-27","cited_by_count":25,"area":"mechinterp"},{"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":"2409.18786","title":"A Survey on the Honesty of Large Language Models","created":"2024-09-27","cited_by_count":23,"area":"alignment"},{"id":"2504.14045","title":"Metacognition and Uncertainty Communication in Humans and Large Language Models","created":"2025-04-18","cited_by_count":23,"area":null},{"id":"2407.13934","title":"Towards Trustworthy AI: A Review of Ethical and Robust Large Language Models","created":"2024-06-01","cited_by_count":22,"area":null},{"id":"2502.12858","title":"Rejected Dialects: Biases Against African American Language in Reward Models","created":"2025-02-18","cited_by_count":20,"area":"alignment"},{"id":"2603.26233","title":"Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents","created":"2026-03-27","cited_by_count":19,"area":"agents"},{"id":"2402.13213","title":"Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A","created":"2024-02-20","cited_by_count":16,"area":null},{"id":"2407.07950","title":"Rel-A.I.: An Interaction-Centered Approach To Measuring Human-LM Reliance","created":"2024-07-10","cited_by_count":16,"area":null},{"id":"2505.24778","title":"Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models' Uncertainty?","created":"2025-05-30","cited_by_count":16,"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":"2405.21028","title":"LACIE: Listener-Aware Finetuning for Confidence Calibration in Large Language Models","created":"2024-05-31","cited_by_count":15,"area":null},{"id":"2407.15814","title":"Perceptions of Linguistic Uncertainty by Language Models and Humans","created":"2024-07-22","cited_by_count":15,"area":null},{"id":"2403.05750","title":"Decoding the AI Pen: Techniques and Challenges in Detecting AI-Generated Text","created":"2024-03-09","cited_by_count":14,"area":null},{"id":"2406.15948","title":"Teaching LLMs to Abstain across Languages via Multilingual Feedback","created":"2024-06-22","cited_by_count":14,"area":null},{"id":"2503.14481","title":"Don't lie to your friends: Learning what you know from collaborative self-play","created":"2025-03-18","cited_by_count":14,"area":null},{"id":"2507.10587","title":"Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missing","created":"2025-07-11","cited_by_count":14,"area":null},{"id":"2503.02233","title":"Enhancing LLM Reliability via Explicit Knowledge Boundary Modeling","created":"2025-03-04","cited_by_count":13,"area":null},{"id":"2503.14749","title":"Uncertainty Distillation: Teaching Language Models to Express Semantic Confidence","created":"2025-03-18","cited_by_count":13,"area":null},{"id":"2404.06283","title":"LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statements","created":"2024-04-09","cited_by_count":12,"area":null},{"id":"2406.03442","title":"Are language models rational? The case of coherence norms and belief revision","created":"2024-06-05","cited_by_count":10,"area":null},{"id":"2405.05966","title":"Natural Language Processing RELIES on Linguistics","created":"2024-05-09","cited_by_count":9,"area":null},{"id":"2510.15232","title":"FinTrust: A Comprehensive Benchmark of Trustworthiness Evaluation in Finance Domain","created":"2025-10-17","cited_by_count":8,"area":null},{"id":"2411.06528","title":"Epistemic Integrity in Large Language Models","created":"2024-11-10","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":"2402.11707","title":"Search Engines Post-ChatGPT: How Generative Artificial Intelligence Could Make Search Less Reliable","created":"2024-02-18","cited_by_count":6,"area":null},{"id":"2410.20199","title":"Rethinking the Uncertainty: A Critical Review and Analysis in the Era of Large Language Models","created":"2024-10-26","cited_by_count":6,"area":"lr"},{"id":"2411.08891","title":"Reliable Decision Making via Calibration Oriented Retrieval Augmented Generation","created":"2024-10-28","cited_by_count":6,"area":"rag"},{"id":"2502.13321","title":"Adjust for Trust: Mitigating Trust-Induced Inappropriate Reliance on AI Assistance","created":"2025-02-18","cited_by_count":6,"area":null},{"id":"2409.20042","title":"Beyond Scores: A Modular RAG-Based System for Automatic Short Answer Scoring with Feedback","created":"2024-09-30","cited_by_count":5,"area":null},{"id":"2502.19684","title":"GRACE: A Granular Benchmark for Evaluating Model Calibration against Human Calibration","created":"2025-02-27","cited_by_count":5,"area":null},{"id":"2505.23804","title":"Calibrating LLMs for Text-to-SQL Parsing by Leveraging Sub-clause Frequencies","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2509.24988","title":"Generalized Correctness Models: Learning Calibrated and Model-Agnostic Correctness Predictors from Historical Patterns","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2512.02914","title":"Martingale Score: An Unsupervised Metric for Bayesian Rationality in LLM Reasoning","created":"2025-12-02","cited_by_count":5,"area":"lr"},{"id":"2605.01428","title":"Hallucinations Undermine Trust; Metacognition is a Way Forward","created":"2026-05-02","cited_by_count":5,"area":null},{"id":"2504.18346","title":"Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Review","created":"2025-04-25","cited_by_count":4,"area":null},{"id":"2508.08992","title":"Rethinking Prospect Theory for LLMs: Revealing the Instability of Decision-Making under Epistemic Uncertainty","created":"2025-08-12","cited_by_count":4,"area":"lr"},{"id":"2510.05126","title":"Generalization of Fine-Tuned Uncertainty Communication and Metacognition in Large Language Models","created":"2025-09-30","cited_by_count":4,"area":null},{"id":"2601.10645","title":"Influential Training Data Retrieval for Explaining Verbalized Confidence of LLMs","created":"2026-01-15","cited_by_count":4,"area":null},{"id":"2604.06714","title":"Steering the Verifiability of Multimodal AI Hallucinations","created":"2026-04-08","cited_by_count":4,"area":"mllm"},{"id":"2408.08212","title":"Covert Bias: The Severity of Social Views' Unalignment in Language Models Towards Implicit and Explicit Opinion","created":"2024-08-15","cited_by_count":3,"area":null},{"id":"2506.01512","title":"Representations of Fact, Fiction and Forecast in Large Language Models: Epistemics and Attitudes","created":"2025-06-02","cited_by_count":3,"area":null},{"id":"2507.06306","title":"Humans overrely on overconfident language models, across languages","created":"2025-07-08","cited_by_count":3,"area":null},{"id":"2510.06370","title":"EVALUESTEER: Measuring Reward Model Steerability Towards Values and Preferences","created":"2025-10-07","cited_by_count":3,"area":"alignment"},{"id":"2601.08064","title":"Calibration Is Not Enough: Evaluating Confidence Estimation Under Language Variations","created":"2026-01-12","cited_by_count":3,"area":null},{"id":"2603.09309","title":"Rescaling Confidence: What Scale Design Reveals About LLM Metacognition","created":"2026-03-10","cited_by_count":3,"area":null},{"id":"2603.15423","title":"Invisible failures in human-AI interactions","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2405.06703","title":"Interpretable Cross-Examination Technique (ICE-T): Using highly informative features to boost LLM performance","created":"2024-05-08","cited_by_count":2,"area":null},{"id":"2505.23996","title":"Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2507.15715","title":"From Queries to Criteria: Understanding How Astronomers Evaluate LLMs","created":"2025-07-21","cited_by_count":2,"area":null},{"id":"2510.08915","title":"Artificial Impressions: Evaluating Large Language Model Behavior Through the Lens of Trait Impressions","created":"2025-10-10","cited_by_count":2,"area":null},{"id":"2603.00883","title":"Knowledge without Wisdom: Measuring Misalignment between LLMs and Intended Impact","created":"2026-03-01","cited_by_count":2,"area":null},{"id":"2605.17480","title":"The Capability Paradox: How Smarter Auditors Make Multi-Agent Systems Less Secure","created":"2026-05-17","cited_by_count":2,"area":"agents"},{"id":"2605.28778","title":"Can LLMs Use Linguistic Uncertainty Markers to Reliably Reflect Intrinsic Confidence?","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2606.17312","title":"Quantifying Consistency in LLM Logical Reasoning via Structural Uncertainty","created":"2026-06-15","cited_by_count":2,"area":"lr"},{"id":"2412.18120","title":"Do Language Models Understand the Cognitive Tasks Given to Them? Investigations with the N-Back Paradigm","created":"2024-12-24","cited_by_count":1,"area":null},{"id":"2506.16724","title":"The Role of Model Confidence on Bias Effects in Measured Uncertainties for Vision-Language Models","created":"2025-06-20","cited_by_count":1,"area":"mllm"},{"id":"2508.07095","title":"Hide or Highlight: Understanding the Impact of Factuality Expression on User Trust","created":"2025-08-09","cited_by_count":1,"area":null},{"id":"2601.18901","title":"Self-Aware Knowledge Probing: Evaluating Language Models' Relational Knowledge through Confidence Calibration","created":"2026-01-26","cited_by_count":1,"area":null},{"id":"2603.29466","title":"An Isotropic Approach to Efficient Uncertainty Quantification with Gradient Norms","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2604.01586","title":"SHOE: Semantic HOI Open-Vocabulary Evaluation Metric","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2604.02830","title":"GRADE: Probing Knowledge Gaps in LLMs through Gradient Subspace Dynamics","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2604.17843","title":"Learning from AVA: Early Lessons from a Curated and Trustworthy Generative AI for Policy and Development Research","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2605.01302","title":"Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generation","created":"2026-05-02","cited_by_count":1,"area":"rag"},{"id":"2606.22179","title":"The Score Granularity Gap in Black-Box LLM Classification: A Comparative Study of Confidence Constructions","created":"2026-06-20","cited_by_count":1,"area":null},{"id":"2609.26489","title":"Calibration as a First-Class Criterion in LLM Evaluation","created":"2026-09-22","cited_by_count":1,"area":null},{"id":"2508.14032","title":"The Promise of Large Language Models in Digital Health: Evidence from Sentiment Analysis in Online Health Communities","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2509.08809","title":"Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals","created":"2025-09-10","cited_by_count":0,"area":"agents"},{"id":"2511.19719","title":"Can LLMs Faithfully Explain Themselves in Low-Resource Languages? A Case Study on Emotion Detection in Persian","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2603.04820","title":"Autoscoring Anticlimax: A Meta-analytic Understanding of AI's Short-answer Shortcomings and Wording Weaknesses","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2604.08454","title":"Less Data Approximates More: Earning Faithful Confidence in High-Stakes Domains","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.12311","title":"Is Vibe Coding the Future? An Empirical Assessment of LLM Generated Codes for Construction Safety","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.03971","title":"Logical Consistency as a Bridge: Improving LLM Hallucination Detection via Label Constraint Modeling between Responses and Self-Judgments","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2606.06673","title":"Uncertainty-Aware LLM-Guided Policy Shaping for Sparse-Reward Reinforcement Learning","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.07951","title":"From 'May' to 'Is': Certainty Distortion in Language Model Rewriting","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2607.22305","title":"A Roadmap to Impactful Pluralistic Alignment Research","created":"2026-07-24","cited_by_count":0,"area":"alignment"},{"id":"2607.25953","title":"Polistemics: Evaluating LLMs as Information Mediators in Politics & Elections","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.17809","title":"Whether LLMs Can Navigate Beliefs and Facts Depends on How You Phrase It","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.18106","title":"Different Facets of Verbalised Overconfidence: an Interpretability Study","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2608.19323","title":"Improved Confidence Estimates for Black-Box Large Language Models","created":"2026-08-19","cited_by_count":0,"area":null}],"next_cursor":"100"}