{"total":73,"rows":[{"id":"2405.05904","title":"Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?","created":"2024-05-09","cited_by_count":232,"area":null},{"id":"2412.05563","title":"A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions","created":"2024-12-07","cited_by_count":121,"area":null},{"id":"2502.06233","title":"Confidence Improves Self-Consistency in LLMs","created":"2025-02-10","cited_by_count":113,"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":"2503.03750","title":"The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems","created":"2025-03-05","cited_by_count":72,"area":"agents"},{"id":"2403.18349","title":"Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedback","created":"2024-03-27","cited_by_count":66,"area":"alignment"},{"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":"2502.04381","title":"Limitations of Large Language Models in Clinical Problem-Solving Arising from Inflexible Reasoning","created":"2025-02-05","cited_by_count":31,"area":"lr"},{"id":"2404.08700","title":"DyKnow: Dynamically Verifying Time-Sensitive Factual Knowledge in LLMs","created":"2024-04-10","cited_by_count":24,"area":null},{"id":"2406.11278","title":"Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs","created":"2024-06-17","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":"2406.00380","title":"HonestLLM: Toward an Honest and Helpful Large Language Model","created":"2024-06-01","cited_by_count":18,"area":null},{"id":"2508.14496","title":"Semantic Energy: Detecting LLM Hallucination Beyond Entropy","created":"2025-08-20","cited_by_count":18,"area":null},{"id":"2410.10857","title":"Mirror-Consistency: Harnessing Inconsistency in Majority Voting","created":"2024-10-07","cited_by_count":17,"area":"lr"},{"id":"2503.06708","title":"Alignment for Efficient Tool Calling of Large Language Models","created":"2025-03-09","cited_by_count":17,"area":"agents"},{"id":"2502.05253","title":"LLMs Can Teach Themselves to Better Predict the Future","created":"2025-02-07","cited_by_count":14,"area":"lr"},{"id":"2602.13110","title":"SCOPE: Selective Conformal Optimized Pairwise LLM Judging","created":"2026-02-13","cited_by_count":14,"area":null},{"id":"2410.06615","title":"QA-Calibration of Language Model Confidence Scores","created":"2024-10-09","cited_by_count":13,"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":"2502.19830","title":"Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation","created":"2025-02-27","cited_by_count":11,"area":"lr"},{"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":"2508.21787","title":"PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chains","created":"2025-08-29","cited_by_count":10,"area":"lr"},{"id":"2511.00280","title":"Calibration Across Layers: Understanding Calibration Evolution in LLMs","created":"2025-10-31","cited_by_count":9,"area":null},{"id":"2512.22245","title":"Calibrating LLM Judges: Linear Probes for Fast and Reliable Uncertainty Estimation","created":"2025-12-23","cited_by_count":9,"area":"mechinterp"},{"id":"2602.05395","title":"Optimal Bayesian Stopping for Efficient Inference of Consistent LLM Answers","created":"2026-02-05","cited_by_count":8,"area":null},{"id":"2410.17389","title":"Navigating Noisy Feedback: Enhancing Reinforcement Learning with Error-Prone Language Models","created":"2024-10-22","cited_by_count":7,"area":"alignment"},{"id":"2507.03279","title":"Conformal Information Pursuit for Interactively Guiding Large Language Models","created":"2025-07-04","cited_by_count":7,"area":null},{"id":"2410.18574","title":"SIKeD: Self-guided Iterative Knowledge Distillation for mathematical reasoning","created":"2024-10-24","cited_by_count":6,"area":"lr"},{"id":"2505.18545","title":"B-score: Detecting biases in large language models using response history","created":"2025-05-24","cited_by_count":6,"area":null},{"id":"2507.09279","title":"Prompt4Trust: A Reinforcement Learning Prompt Augmentation Framework for Clinically-Aligned Confidence Calibration in Multimodal Large Language Models","created":"2025-07-12","cited_by_count":6,"area":"mllm"},{"id":"2507.19477","title":"Advancing Event Forecasting through Massive Training of Large Language Models: Challenges, Solutions, and Broader Impacts","created":"2025-07-25","cited_by_count":6,"area":null},{"id":"2601.11004","title":"NOVA: NOise-aware Verbal Confidence CAlibration for Robust Large Language Models in RAG Systems","created":"2026-01-16","cited_by_count":6,"area":"rag"},{"id":"2605.27752","title":"Same Answer, Different Confidence: Protocol Sensitivity in LLM Confidence Calibration","created":"2026-05-26","cited_by_count":6,"area":null},{"id":"2509.01476","title":"Do Retrieval Augmented Language Models Know When They Don't Know?","created":"2025-09-01","cited_by_count":5,"area":"rag"},{"id":"2603.16728","title":"The Cost of Reasoning: Chain-of-Thought Induces Overconfidence in Vision-Language Models","created":"2026-03-17","cited_by_count":5,"area":"lr"},{"id":"2503.06709","title":"Delusions of Large Language Models","created":"2025-03-09","cited_by_count":4,"area":null},{"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":"2511.09228","title":"Taming Object Hallucinations with Verified Atomic Confidence Estimation","created":"2025-11-12","cited_by_count":4,"area":"mllm"},{"id":"2506.02659","title":"Are Economists Always More Introverted? Analyzing Consistency in Persona-Assigned LLMs","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2509.12908","title":"All Roads Lead to Rome: Graph-Based Confidence Estimation for Large Language Model Reasoning","created":"2025-09-16","cited_by_count":3,"area":"lr"},{"id":"2510.20460","title":"Systematic Evaluation of Uncertainty Estimation Methods in Large Language Models","created":"2025-10-23","cited_by_count":3,"area":null},{"id":"2602.07842","title":"Evaluating and Calibrating LLM Confidence on Questions with Multiple Correct Answers","created":"2026-02-08","cited_by_count":3,"area":null},{"id":"2604.17200","title":"Calibrating Model-Based Evaluation Metrics for Summarization","created":"2026-04-19","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":"2410.05802","title":"Gradual Learning: Optimizing Fine-Tuning with Partially Mastered Knowledge in Large Language Models","created":"2024-10-08","cited_by_count":2,"area":null},{"id":"2504.18880","title":"Reshaping MOFs text mining with a dynamic multi-agents framework of large language model","created":"2025-04-26","cited_by_count":2,"area":null},{"id":"2507.18182","title":"SCOPE: Stochastic and Counterbiased Option Placement for Evaluating Large Language Models","created":"2025-07-24","cited_by_count":2,"area":null},{"id":"2602.13571","title":"LLM-Confidence Reranker: A Training-Free Approach for Enhancing Retrieval-Augmented Generation Systems","created":"2026-02-14","cited_by_count":2,"area":"rag"},{"id":"2603.03417","title":"Parallel Test-Time Scaling with Multi-Sequence Verifiers","created":"2026-03-03","cited_by_count":2,"area":"lr"},{"id":"2603.15653","title":"Recursive Language Models Meet Uncertainty: The Surprising Effectiveness of Self-Reflective Program Search for Long Context","created":"2026-03-07","cited_by_count":2,"area":null},{"id":"2605.06053","title":"Towards Generation-Efficient Uncertainty Estimation in Large Language Models","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2605.10415","title":"Aligning LLM Uncertainty with Human Disagreement in Subjectivity Analysis","created":"2026-05-11","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":"2607.03528","title":"Aligning Language Models with Selective Prediction","created":"2026-07-03","cited_by_count":2,"area":"alignment"},{"id":"2602.01956","title":"Efficient Epistemic Uncertainty Estimation for Large Language Models via Knowledge Distillation","created":"2026-02-02","cited_by_count":1,"area":"distill"},{"id":"2602.16039","title":"How Uncertain Is the Grade? A Benchmark of Uncertainty Metrics for LLM-Based Automatic Assessment","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2604.05952","title":"Towards Trustworthy Report Generation: A Deep Research Agent with Progressive Confidence Estimation and Calibration","created":"2026-04-07","cited_by_count":1,"area":"agents"},{"id":"2605.00326","title":"Prompt-Induced Score Variance in Zero-Shot Binary Vision-Language Safety Classification","created":"2026-05-01","cited_by_count":1,"area":"mllm"},{"id":"2605.08432","title":"A Semantic-Sampling Framework for Evaluating Calibration in Open-Ended Question Answering","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2606.05799","title":"CaliDist: Calibrating Large Language Models via Behavioral Robustness to Distraction","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2608.02677","title":"When Policies Change Probabilities: Modular Decision-Making for LLM Code Review","created":"2026-08-02","cited_by_count":1,"area":null},{"id":"2407.03004","title":"SemioLLM: Evaluating Large Language Models for Diagnostic Reasoning from Unstructured Clinical Narratives in Epilepsy","created":"2024-07-03","cited_by_count":0,"area":"lr"},{"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":"2505.14852","title":"EasyMath: A 0-shot Math Benchmark for SLMs","created":"2025-05-20","cited_by_count":0,"area":"lr"},{"id":"2601.11866","title":"Advances in LLM Reasoning Enable Flexibility in Clinical Problem-Solving","created":"2026-01-17","cited_by_count":0,"area":"lr"},{"id":"2603.07867","title":"Slumbering to Precision: Enhancing Artificial Neural Network Calibration Through Sleep-like Processes","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2606.13591","title":"Confidence Composition for Multiagent Language Model Systems","created":"2026-06-11","cited_by_count":0,"area":"lr"},{"id":"2606.23671","title":"Can LLMs Reliably Self-Report Adversarial Prefills, and How?","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2608.07827","title":"From token probabilities to calibrated confidence: An empirical study of mathematical question answering","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.11275","title":"Every pooling rule has its world: matching probability combination rules to situations and stakes","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.16650","title":"PCA-guided Activation Scaling for Monotonic Bidirectional Control over LLM Sycophancy","created":"2026-08-17","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":"2610.02695","title":"Test-time Calibration Learning for Large Language Model Reasoning","created":"2026-10-02","cited_by_count":0,"area":"lr"}],"next_cursor":null}