{"total":40,"rows":[{"id":"2412.12472","title":"Knowledge Boundary of Large Language Models: A Survey","created":"2024-12-17","cited_by_count":40,"area":null},{"id":"2506.07461","title":"From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centered","created":"2025-06-09","cited_by_count":21,"area":null},{"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":"2505.17510","title":"Large Language Models Do Multi-Label Classification Differently","created":"2025-05-23","cited_by_count":13,"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":"2509.03116","title":"Measuring Scalar Constructs in Social Science with LLMs","created":"2025-09-03","cited_by_count":9,"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":"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":"2604.05306","title":"LLMs Should Express Uncertainty Explicitly","created":"2026-04-07","cited_by_count":6,"area":null},{"id":"2509.24510","title":"Specialization after Generalization: Towards Understanding Test-Time Training in Foundation Models","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2602.13699","title":"Gradient-Stable Attention Heads Signal LLM Correctness","created":"2026-02-14","cited_by_count":5,"area":null},{"id":"2509.16696","title":"Decoding Uncertainty: The Impact of Decoding Strategies for Uncertainty Estimation in Large Language Models","created":"2025-09-20","cited_by_count":3,"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":"2604.07172","title":"Improving Semantic Uncertainty Quantification in Language Model Question-Answering via Token-Level Temperature Scaling","created":"2026-04-08","cited_by_count":2,"area":null},{"id":"2605.19999","title":"LLM Benchmark Datasets Should Be Contamination-Resistant","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2605.22007","title":"Hallucination as Commitment Failure: Larger LLMs Misfire Despite Knowing the Answer","created":"2026-05-21","cited_by_count":2,"area":null},{"id":"2505.03819","title":"Focus on Likely Classes for Test-Time Prediction","created":"2025-05-02","cited_by_count":1,"area":null},{"id":"2506.01817","title":"BD at BEA 2025 Shared Task: MPNet Ensembles for Pedagogical Mistake Identification and Localization in AI Tutor Responses","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2601.04277","title":"Unlocking the Pre-Trained Model as a Dual-Alignment Calibrator for Post-Trained LLMs","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2602.14862","title":"The Well-Tempered Classifier: Some Elementary Properties of Temperature Scaling","created":"2026-02-16","cited_by_count":1,"area":null},{"id":"2606.09876","title":"Calibrating Overconfidence Without Sacrificing Confidence: Probe-Conditioned Head Intervention for LLMs","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.14909","title":"Audited Conformal Prediction for Classification under Unknown Distribution Shift","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2606.17350","title":"Do Large Language Models Always Tell The Same Stories?","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2412.13695","title":"Optical aberrations in autonomous driving: Physics-informed parameterized temperature scaling for neural network uncertainty calibration","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2506.11046","title":"The Effects of Data Augmentation on Confidence Estimation for LLMs","created":"2025-05-21","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":"2603.11957","title":"CHiL(L)Grader: Calibrated Human-in-the-Loop Short-Answer Grading","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2604.03589","title":"Entropy and Attention Dynamics in Small Language Models: A Trace-Level Structural Analysis on the TruthfulQA Benchmark","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2604.14389","title":"BiCon-Gate: Consistency-Gated De-colloquialisation for Dialogue Fact-Checking","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2605.06294","title":"Log-Likelihood, Simpson's Paradox, and the Detection of Machine-Generated Text","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.10202","title":"Task-Aware Calibration: Provably Optimal Decoding in LLMs","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.13595","title":"Inducing Artificial Uncertainty in Language Models","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.20490","title":"ECUAS$_n$: A family of metrics for principled evaluation of uncertainty-augmented systems","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2607.04389","title":"Decentralized Aggregation of LLM Predictions via Wagering Mechanisms","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2608.10315","title":"Is This Your Final Answer? Cross-Contextual Consistency as a Measure of LLM Credibility","created":"2026-08-10","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":"2609.11446","title":"Calibration-Aware Uncertainty Cascades for Efficient Heterogeneous Model Collaboration","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.36689","title":"CHAIN: Calibrated LLM Forecasting via Causal-Temporal Hypergraph Inference","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.00381","title":"OmniMed-Jev: Calibrating LVLM Confidence for Trustworthy Medical Multimodal Decisions via System One","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}