{"total":91,"rows":[{"id":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401,"area":null},{"id":"2311.08298","title":"A Survey of Confidence Estimation and Calibration in Large Language Models","created":"2023-11-14","cited_by_count":256,"area":null},{"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":"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":"2412.14737","title":"On Verbalized Confidence Scores for LLMs","created":"2024-12-19","cited_by_count":83,"area":null},{"id":"2405.00623","title":"\"I'm Not Sure, But...\": Examining the Impact of Large Language Models' Uncertainty Expression on User Reliance and Trust","created":"2024-05-01","cited_by_count":67,"area":null},{"id":"2410.13284","title":"Learning to Route LLMs with Confidence Tokens","created":"2024-10-17","cited_by_count":67,"area":null},{"id":"2503.00172","title":"A Survey of Uncertainty Estimation Methods on Large Language Models","created":"2025-02-28","cited_by_count":62,"area":null},{"id":"2504.06514","title":"Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?","created":"2025-04-09","cited_by_count":58,"area":"lr"},{"id":"2402.02047","title":"Calibration and Correctness of Language Models for Code","created":"2024-02-03","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":"2406.04306","title":"Improving Uncertainty Estimation through Semantically Diverse Language Generation","created":"2024-06-06","cited_by_count":35,"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":"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":"2404.09127","title":"Confidence Calibration and Rationalization for LLMs via Multi-Agent Deliberation","created":"2024-04-14","cited_by_count":26,"area":"agents"},{"id":"2409.12180","title":"Finetuning Language Models to Emit Linguistic Expressions of Uncertainty","created":"2024-09-18","cited_by_count":26,"area":null},{"id":"2406.05392","title":"Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey","created":"2024-06-08","cited_by_count":23,"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":"2401.15170","title":"Scalable Qualitative Coding with LLMs: Chain-of-Thought Reasoning Matches Human Performance in Some Hermeneutic Tasks","created":"2024-01-26","cited_by_count":22,"area":"lr"},{"id":"2402.11253","title":"Aligning Large Language Models by On-Policy Self-Judgment","created":"2024-02-17","cited_by_count":20,"area":"alignment"},{"id":"2502.10709","title":"An Empirical Analysis of Uncertainty in Large Language Model Evaluations","created":"2025-02-15","cited_by_count":20,"area":null},{"id":"2503.02863","title":"SteerConf: Steering LLMs for Confidence Elicitation","created":"2025-03-04","cited_by_count":20,"area":null},{"id":"2504.07863","title":"Robust Hallucination Detection in LLMs via Adaptive Token Selection","created":"2025-04-10","cited_by_count":19,"area":null},{"id":"2412.15176","title":"Rethinking Uncertainty Estimation in LLMs: A Principled Single-Sequence Measure","created":"2024-12-19","cited_by_count":18,"area":"lr"},{"id":"2505.11462","title":"Disentangling Reasoning and Knowledge in Medical Large Language Models","created":"2025-05-16","cited_by_count":18,"area":"lr"},{"id":"2508.06225","title":"Overconfidence in LLM-as-a-Judge: Diagnosis and Confidence-Driven Solution","created":"2025-08-08","cited_by_count":18,"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":"2406.15948","title":"Teaching LLMs to Abstain across Languages via Multilingual Feedback","created":"2024-06-22","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":"2412.11803","title":"UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models","created":"2024-12-16","cited_by_count":13,"area":"alignment"},{"id":"2505.16922","title":"UNCLE: Benchmarking Uncertainty Expressions in Long-Form Generation","created":"2025-05-22","cited_by_count":11,"area":null},{"id":"2505.23224","title":"MMBoundary: Advancing MLLM Knowledge Boundary Awareness through Reasoning Step Confidence Calibration","created":"2025-05-29","cited_by_count":11,"area":"lr"},{"id":"2601.04435","title":"Accommodation and Epistemic Vigilance: A Pragmatic Account of Why LLMs Fail to Challenge Harmful Beliefs","created":"2026-01-07","cited_by_count":11,"area":null},{"id":"2505.19184","title":"When Two LLMs Debate, Both Think They'll Win","created":"2025-05-25","cited_by_count":10,"area":"lr"},{"id":"2504.05312","title":"Towards Adaptive Memory-Based Optimization for Enhanced Retrieval-Augmented Generation","created":"2025-02-19","cited_by_count":9,"area":"rag"},{"id":"2604.16830","title":"The Illusion of Certainty: Decoupling Capability and Calibration in On-Policy Distillation","created":"2026-04-18","cited_by_count":9,"area":"distill"},{"id":"2411.06528","title":"Epistemic Integrity in Large Language Models","created":"2024-11-10","cited_by_count":7,"area":null},{"id":"2411.16742","title":"Text-to-SQL Calibration: No Need to Ask -- Just Rescale Model Probabilities","created":"2024-11-23","cited_by_count":7,"area":null},{"id":"2504.19622","title":"From Evidence to Belief: A Bayesian Epistemology Approach to Language Models","created":"2025-04-28","cited_by_count":6,"area":null},{"id":"2508.12040","title":"Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation","created":"2025-08-16","cited_by_count":6,"area":null},{"id":"2508.15050","title":"Don't Think Twice! Over-Reasoning Impairs Confidence Calibration","created":"2025-08-20","cited_by_count":6,"area":"lr"},{"id":"2511.08991","title":"Robust Sampling for Active Statistical Inference","created":"2025-11-12","cited_by_count":6,"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":"2512.07404","title":"On LLMs' Internal Representation of Code Correctness","created":"2025-12-08","cited_by_count":5,"area":null},{"id":"2402.13606","title":"MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models","created":"2024-02-21","cited_by_count":4,"area":null},{"id":"2504.09895","title":"Learning from Reference Answers: Versatile Language Model Alignment without Binary Human Preference Data","created":"2025-04-14","cited_by_count":4,"area":"alignment"},{"id":"2506.07309","title":"ConfRAG: Confidence-Guided Retrieval-Augmenting Generation","created":"2025-06-08","cited_by_count":4,"area":"rag"},{"id":"2508.08661","title":"Hallucinations in Code Change to Natural Language Generation: Prevalence and Evaluation of Detection Metrics","created":"2025-08-12","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":"2511.08968","title":"Bayesian Mixture of Experts For Large Language Models","created":"2025-11-12","cited_by_count":4,"area":"moe"},{"id":"2511.09228","title":"Taming Object Hallucinations with Verified Atomic Confidence Estimation","created":"2025-11-12","cited_by_count":4,"area":"mllm"},{"id":"2503.11381","title":"Modeling Subjectivity in Cognitive Appraisal with Language Models","created":"2025-03-14","cited_by_count":3,"area":null},{"id":"2505.22318","title":"Flying Pigs, FaR and Beyond: Evaluating LLM Reasoning in Counterfactual Worlds","created":"2025-05-28","cited_by_count":3,"area":"lr"},{"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":"2507.06489","title":"On the Robustness of Verbal Confidence of LLMs in Adversarial Attacks","created":"2025-07-09","cited_by_count":3,"area":null},{"id":"2604.19444","title":"Unsupervised Confidence Calibration for Reasoning LLMs from a Single Generation","created":"2026-04-21","cited_by_count":3,"area":"lr"},{"id":"2604.24470","title":"Zero-shot Large Language Models for Automatic Readability Assessment","created":"2026-04-27","cited_by_count":3,"area":null},{"id":"2605.26366","title":"Automatic Layer Selection for Hallucination Detection","created":"2026-05-25","cited_by_count":3,"area":null},{"id":"2503.12528","title":"Investigating Human-Aligned Large Language Model Uncertainty","created":"2025-03-16","cited_by_count":2,"area":"alignment"},{"id":"2506.02696","title":"Shaking to Reveal: Perturbation-Based Detection of LLM Hallucinations","created":"2025-06-03","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":"2601.09241","title":"When to Trust: A Causality-Aware Calibration Framework for Accurate Knowledge Graph Retrieval-Augmented Generation","created":"2026-01-14","cited_by_count":2,"area":"rag"},{"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":"2605.28778","title":"Can LLMs Use Linguistic Uncertainty Markers to Reliably Reflect Intrinsic Confidence?","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2608.14320","title":"AnchorBench: A Multi-Pathway Benchmark for the Anchoring Effect in LLMs","created":"2026-08-14","cited_by_count":2,"area":null},{"id":"2502.01691","title":"Agent-Based Uncertainty Awareness Improves Automated Radiology Report Labeling with an Open-Source Large Language Model","created":"2025-02-02","cited_by_count":1,"area":"agents"},{"id":"2502.19463","title":"Hedging and Non-Affirmation: Quantifying LLM Alignment on Questions of Human Rights","created":"2025-02-26","cited_by_count":1,"area":"alignment"},{"id":"2505.11731","title":"Dist2ill: Distributional Distillation for One-Pass Uncertainty Estimation in Large Language Models","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2505.17855","title":"Explaining Sources of Uncertainty in Automated Fact-Checking","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2506.06540","title":"Large Language Models Can Be a Viable Substitute for Expert Political Surveys When a Shock Disrupts Traditional Measurement Approaches","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2510.15977","title":"Bolster Hallucination Detection via Prompt-Guided Data Augmentation","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2601.23094","title":"Safer Policy Compliance with Dynamic Epistemic Fallback","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2607.11881","title":"Metacognition in LLMs: Foundations, Progress, and Opportunities","created":"2026-07-13","cited_by_count":1,"area":null},{"id":"2607.23976","title":"This Is a Good Paper, Right? How Tag Questions Affect Sycophancy Across 106 Language Models","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2408.12326","title":"Interactive DualChecker for Mitigating Hallucinations in Distilling Large Language Models","created":"2024-08-22","cited_by_count":0,"area":"distill"},{"id":"2410.12478","title":"MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2508.08204","title":"Human-Alignment and Calibration of Inference-Time Uncertainty in Large Language Models","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2510.17727","title":"Enabling Fine-Grained Operating Points for Black-Box LLMs","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2603.27033","title":"RealBirdID: Benchmarking Bird Species Identification in the Era of MLLMs","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2604.14651","title":"CURA: Clinical Uncertainty Risk Alignment for Language Model-Based Risk Prediction","created":"2026-04-16","cited_by_count":0,"area":"alignment"},{"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":"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":"2608.20717","title":"DirEAG: Dirichlet Evidence Aggregation for Calibrating Verbalized Confidence in Mathematical Reasoning","created":"2026-08-21","cited_by_count":0,"area":"lr"},{"id":"2609.15319","title":"Clean Scores, Buried Evidence, and Confident Wrong: A Receipt-Based Audit of Frontier Agentic QA","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.26035","title":"Truth for Believable AI: Expressed Doubt, Provenance, and Belief Revision as an Engineerable Stance","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2610.00083","title":"\"very likely\" Means \"uncertain\"? How LLMs Diverge from Humans in Linguistic Uncertainty Quantification","created":"2026-09-06","cited_by_count":0,"area":null}],"next_cursor":null}