{"total":73,"rows":[{"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":"2502.08606","title":"Distillation Scaling Laws","created":"2025-02-12","cited_by_count":67,"area":"lr"},{"id":"2505.23646","title":"Are Reasoning Models More Prone to Hallucination?","created":"2025-05-29","cited_by_count":64,"area":"lr"},{"id":"2510.17516","title":"SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors","created":"2025-10-20","cited_by_count":52,"area":null},{"id":"2412.14516","title":"Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment","created":"2024-12-19","cited_by_count":51,"area":"alignment"},{"id":"2406.19215","title":"SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation","created":"2024-06-27","cited_by_count":40,"area":"rag"},{"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":"2403.08819","title":"Thermometer: Towards Universal Calibration for Large Language Models","created":"2024-02-20","cited_by_count":38,"area":null},{"id":"2404.09610","title":"LoRA Dropout as a Sparsity Regularizer for Overfitting Control","created":"2024-04-15","cited_by_count":35,"area":null},{"id":"2403.00025","title":"On the Challenges and Opportunities in Generative AI","created":"2024-02-28","cited_by_count":31,"area":null},{"id":"2312.07401","title":"On Diversified Preferences of Large Language Model Alignment","created":"2023-12-12","cited_by_count":26,"area":"alignment"},{"id":"2410.13246","title":"Atomic Calibration of LLMs in Long-Form Generations","created":"2024-10-17","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":"2410.10414","title":"On Calibration of LLM-based Guard Models for Reliable Content Moderation","created":"2024-10-14","cited_by_count":23,"area":"safety"},{"id":"2505.23854","title":"Revisiting Uncertainty Estimation and Calibration of Large Language Models","created":"2025-05-29","cited_by_count":23,"area":"moe"},{"id":"2402.11253","title":"Aligning Large Language Models by On-Policy Self-Judgment","created":"2024-02-17","cited_by_count":20,"area":"alignment"},{"id":"2505.16690","title":"Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator","created":"2025-05-22","cited_by_count":20,"area":null},{"id":"2510.00526","title":"Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum","created":"2025-10-01","cited_by_count":18,"area":null},{"id":"2505.23912","title":"LoVeC: Reinforcement Learning for Better Verbalized Confidence in Long-Form Generations","created":"2025-05-29","cited_by_count":17,"area":null},{"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":"2406.01806","title":"Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language Generation","created":"2024-06-03","cited_by_count":16,"area":null},{"id":"2503.16870","title":"Sparse Logit Sampling: Accelerating Knowledge Distillation in LLMs","created":"2025-03-21","cited_by_count":16,"area":"distill"},{"id":"2505.17510","title":"Large Language Models Do Multi-Label Classification Differently","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2505.20903","title":"Towards Objective Fine-tuning: How LLMs' Prior Knowledge Causes Potential Poor Calibration?","created":"2025-05-27","cited_by_count":11,"area":null},{"id":"2506.11887","title":"Cascaded Language Models for Cost-effective Human-AI Decision-Making","created":"2025-06-13","cited_by_count":11,"area":null},{"id":"2506.21408","title":"Scalable Bayesian Low-Rank Adaptation of Large Language Models via Stochastic Variational Subspace Inference","created":"2025-06-26","cited_by_count":11,"area":null},{"id":"2506.23464","title":"The Confidence Paradox: Can LLM Know When It's Wrong","created":"2025-06-30","cited_by_count":11,"area":null},{"id":"2508.15842","title":"Lexical Hints of Accuracy in LLM Reasoning Chains","created":"2025-08-19","cited_by_count":9,"area":"lr"},{"id":"2412.12767","title":"A Survey of Calibration Process for Black-Box LLMs","created":"2024-12-17","cited_by_count":8,"area":null},{"id":"2601.03042","title":"BaseCal: Unsupervised Confidence Calibration via Base Model Signals","created":"2026-01-06","cited_by_count":8,"area":null},{"id":"2404.06742","title":"Transferable and Efficient Non-Factual Content Detection via Probe Training with Offline Consistency Checking","created":"2024-04-10","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":"2507.03279","title":"Conformal Information Pursuit for Interactively Guiding Large Language Models","created":"2025-07-04","cited_by_count":7,"area":null},{"id":"2606.03437","title":"Large Language Models Are Overconfident in Their Own Responses","created":"2026-06-02","cited_by_count":6,"area":null},{"id":"2406.02120","title":"Diver: Large Language Model Decoding with Span-Level Mutual Information Verification","created":"2024-06-04","cited_by_count":5,"area":null},{"id":"2502.06806","title":"Logits are All We Need to Adapt Closed Models","created":"2025-02-03","cited_by_count":5,"area":null},{"id":"2503.01550","title":"None of the Above, Less of the Right: Parallel Patterns between Humans and LLMs on Multi-Choice Questions Answering","created":"2025-03-03","cited_by_count":5,"area":null},{"id":"2404.14642","title":"Uncertainty Quantification on Graph Learning: A Survey","created":"2024-04-23","cited_by_count":4,"area":null},{"id":"2502.11874","title":"VAQUUM: Are Vague Quantifiers Grounded in Visual Data?","created":"2025-02-17","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":"2504.11381","title":"RankAlign: A Ranking View of the Generator-Validator Gap in Large Language Models","created":"2025-04-15","cited_by_count":4,"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":"2601.23096","title":"CATTO: Balancing Preferences and Confidence in Language Models","created":"2026-01-30","cited_by_count":4,"area":"alignment"},{"id":"2603.17218","title":"Alignment Makes Language Models Normative, Not Descriptive","created":"2026-03-17","cited_by_count":4,"area":"alignment"},{"id":"2604.25591","title":"Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Models","created":"2026-04-28","cited_by_count":4,"area":null},{"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":"2502.01458","title":"The Capabilities and Limitations of Weak-to-Strong Generalization: Generalization and Calibration","created":"2025-02-03","cited_by_count":2,"area":null},{"id":"2504.15432","title":"Feeding LLM Annotations to BERT Classifiers at Your Own Risk","created":"2025-04-21","cited_by_count":2,"area":null},{"id":"2504.19391","title":"Bi-directional Model Cascading with Proxy Confidence","created":"2025-04-27","cited_by_count":2,"area":null},{"id":"2509.21284","title":"Bounds of Chain-of-Thought Robustness: Reasoning Steps, Embed Norms, and Beyond","created":"2025-09-25","cited_by_count":2,"area":"lr"},{"id":"2510.06307","title":"Belief-Calibrated Multi-Agent Consensus Seeking for Complex NLP Tasks","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2605.19344","title":"Retrieval-Augmented Linguistic Calibration","created":"2026-05-19","cited_by_count":2,"area":"rag"},{"id":"2505.02072","title":"Express Your Doubts -- Probabilistic World Modeling Should not be Based on Token logprobs","created":"2025-05-04","cited_by_count":1,"area":"wm"},{"id":"2505.24147","title":"Rationales Are Not Silver Bullets: Measuring the Impact of Rationales on Model Performance and Reliability","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2601.09771","title":"PCN-Rec: Agentic Proof-Carrying Negotiation for Reliable Governance-Constrained Recommendation","created":"2026-01-14","cited_by_count":1,"area":"agents"},{"id":"2602.11871","title":"DMAP: A Distribution Map for Text","created":"2026-02-12","cited_by_count":1,"area":null},{"id":"2602.15569","title":"What Are You Doing? Effects of Intermediate Feedback from Agentic LLM In-Car Assistants During Multi-Step Processing","created":"2026-02-17","cited_by_count":1,"area":"agents"},{"id":"2605.31220","title":"Shared Doubt: Zero-Shot Cross-Lingual Confidence Estimation for Language Models","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2608.02966","title":"Every Wrong Answer Counts: Option-Level Psychometrics for LLM Multiple-Choice Benchmarks","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2409.00352","title":"Does Alignment Tuning Really Break LLMs' Internal Confidence?","created":"2024-08-31","cited_by_count":0,"area":null},{"id":"2602.09486","title":"Listen to the Layers: Mitigating Hallucinations with Inter-Layer Disagreement","created":"2026-02-10","cited_by_count":0,"area":null},{"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":"2603.09985","title":"The Dunning-Kruger Effect in Large Language Models: An Empirical Study of Confidence Calibration","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.19744","title":"Rethinking Ground Truth: A Case Study on Human Label Variation in MLLM Benchmarking","created":"2026-03-20","cited_by_count":0,"area":"lr"},{"id":"2604.06723","title":"Fine-grained Approaches for Confidence Calibration of LLMs in Automated Code Revision","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2605.13484","title":"Discovery of Hidden Miscalibration Regimes","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.30447","title":"Calibrated Preference Learning: The Case of Label Ranking","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.19416","title":"MortarBench: Evaluating Mortgage Loan Origination Agents","created":"2026-06-17","cited_by_count":0,"area":"agents"},{"id":"2606.20585","title":"Turning Intent into Specifications: A Benchmark and an Interactive User-Assistant Agent","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2607.20115","title":"Understanding the Impact of Linguistic Realization Choices on LLM Stance with Causal Tracing","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2608.13430","title":"Are You Sure You're Sure? On the Impact of Instruction Tuning on Confidence and Lexical Diversity","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2609.38797","title":"Evaluating Persistent Calibration under Evolving Model Knowledge","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.14961","title":"HiPAD: A Unified Gait, Audio-Visual, and Personality Fusion Network for Depression Detection, with a Hierarchical Personality Ablation and the Calibration Limits of Domain-Adapted LLMs","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}