{"total":91,"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":"2406.09714","title":"Large language model validity via enhanced conformal prediction methods","created":"2024-06-14","cited_by_count":92,"area":null},{"id":"2412.14737","title":"On Verbalized Confidence Scores for LLMs","created":"2024-12-19","cited_by_count":83,"area":null},{"id":"2407.00499","title":"ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guarantees","created":"2024-06-29","cited_by_count":65,"area":null},{"id":"2405.01976","title":"Conformal Prediction for Natural Language Processing: A Survey","created":"2024-05-03","cited_by_count":53,"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":"2407.14614","title":"Evaluating language models as risk scores","created":"2024-07-19","cited_by_count":27,"area":null},{"id":"2408.06816","title":"MAQA: Evaluating Uncertainty Quantification in LLMs Regarding Data Uncertainty","created":"2024-08-13","cited_by_count":27,"area":null},{"id":"2410.14582","title":"Do LLMs estimate uncertainty well in instruction-following?","created":"2024-10-18","cited_by_count":26,"area":null},{"id":"2410.06494","title":"Conformal Prediction: A Data Perspective","created":"2024-10-09","cited_by_count":25,"area":null},{"id":"2407.03658","title":"GPT-4 vs. Human Translators: A Comprehensive Evaluation of Translation Quality Across Languages, Domains, and Expertise Levels","created":"2024-07-04","cited_by_count":21,"area":null},{"id":"2405.11874","title":"xFinder: Large Language Models as Automated Evaluators for Reliable Evaluation","created":"2024-05-20","cited_by_count":19,"area":null},{"id":"2501.00555","title":"Prune 'n Predict: Optimizing LLM Decision-making with Conformal Prediction","created":"2024-12-31","cited_by_count":18,"area":null},{"id":"2408.11316","title":"Probabilistic Medical Predictions of Large Language Models","created":"2024-08-21","cited_by_count":16,"area":null},{"id":"2408.08978","title":"See What LLMs Cannot Answer: A Self-Challenge Framework for Uncovering LLM Weaknesses","created":"2024-08-16","cited_by_count":15,"area":null},{"id":"2411.02381","title":"Addressing Uncertainty in LLMs to Enhance Reliability in Generative AI","created":"2024-11-04","cited_by_count":15,"area":null},{"id":"2504.04462","title":"An overview of model uncertainty and variability in LLM-based sentiment analysis. Challenges, mitigation strategies and the role of explainability","created":"2025-04-06","cited_by_count":15,"area":null},{"id":"2601.12471","title":"Knowing When to Abstain: Medical LLMs Under Clinical Uncertainty","created":"2026-01-18","cited_by_count":15,"area":null},{"id":"2406.04370","title":"Large Language Model Confidence Estimation via Black-Box Access","created":"2024-06-01","cited_by_count":14,"area":null},{"id":"2406.19712","title":"Uncertainty Quantification in Large Language Models Through Convex Hull Analysis","created":"2024-06-28","cited_by_count":13,"area":null},{"id":"2402.07616","title":"Anchor-based Large Language Models","created":"2024-02-12","cited_by_count":12,"area":null},{"id":"2411.02454","title":"Graph-based Confidence Calibration for Large Language Models","created":"2024-11-03","cited_by_count":10,"area":null},{"id":"2504.13787","title":"Probabilistic Stability Guarantees for Feature Attributions","created":"2025-04-18","cited_by_count":9,"area":null},{"id":"2506.18082","title":"Statistical Multicriteria Evaluation of LLM-Generated Text","created":"2025-06-22","cited_by_count":9,"area":null},{"id":"2402.14860","title":"Ranking Large Language Models without Ground Truth","created":"2024-02-21","cited_by_count":8,"area":null},{"id":"2405.19323","title":"Are Large Language Models Chameleons? An Attempt to Simulate Social Surveys","created":"2024-05-29","cited_by_count":8,"area":null},{"id":"2406.12784","title":"UBench: Benchmarking Uncertainty in Large Language Models with Multiple Choice Questions","created":"2024-06-18","cited_by_count":7,"area":null},{"id":"2506.03278","title":"FailureSensorIQ: A Multi-Choice QA Dataset for Understanding Sensor Relationships and Failure Modes","created":"2025-06-03","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":"2404.03818","title":"PRobELM: Plausibility Ranking Evaluation for Language Models","created":"2024-04-04","cited_by_count":6,"area":null},{"id":"2409.03225","title":"Enhancing Healthcare LLM Trust with Atypical Presentations Recalibration","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2410.06431","title":"Functional-level Uncertainty Quantification for Calibrated Fine-tuning on LLMs","created":"2024-10-09","cited_by_count":6,"area":null},{"id":"2510.05566","title":"Domain-Shift-Aware Conformal Prediction for Large Language Models","created":"2025-10-07","cited_by_count":6,"area":null},{"id":"2602.02419","title":"SafeGround: Know When to Trust GUI Grounding Models via Uncertainty Calibration","created":"2026-02-02","cited_by_count":6,"area":null},{"id":"2502.20309","title":"EAIRA: Establishing a Methodology for Evaluating AI Models as Scientific Research Assistants","created":"2025-02-27","cited_by_count":5,"area":null},{"id":"2503.10628","title":"Uncertainty in Action: Confidence Elicitation in Embodied Agents","created":"2025-03-13","cited_by_count":5,"area":null},{"id":"2503.23175","title":"Large Language Models Are Unreliable for Cyber Threat Intelligence","created":"2025-03-29","cited_by_count":5,"area":null},{"id":"2608.28945","title":"Automated Researchers Can Mitigate Well-characterized Alignment Failures","created":"2026-08-28","cited_by_count":5,"area":null},{"id":"2501.11866","title":"Evaluating multiple models using labeled and unlabeled data","created":"2025-01-21","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":"2603.22966","title":"Set-Valued Prediction for Large Language Models with Feasibility-Aware Coverage Guarantees","created":"2026-03-24","cited_by_count":4,"area":null},{"id":"2506.07458","title":"KScope: A Framework for Characterizing the Knowledge Status of Language Models","created":"2025-06-09","cited_by_count":3,"area":null},{"id":"2506.11812","title":"On the Performance of LLMs for Real Estate Appraisal","created":"2025-06-13","cited_by_count":3,"area":null},{"id":"2509.11686","title":"Do Code Semantics Help? A Comprehensive Study on Execution Trace-Based Information for Code Large Language Models","created":"2025-09-15","cited_by_count":3,"area":null},{"id":"2510.08389","title":"Revisiting Hallucination Detection with Effective Rank-based Uncertainty","created":"2025-10-09","cited_by_count":3,"area":null},{"id":"2603.05909","title":"InfoGatherer: Principled Information Seeking via Evidence Retrieval and Strategic Questioning","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2503.22712","title":"Coverage-Guaranteed Speech Emotion Recognition via Calibrated Uncertainty-Adaptive Prediction Sets","created":"2025-03-24","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":"2506.03662","title":"Zero-Shot Temporal Interaction Localization for Egocentric Videos","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2506.11021","title":"Eliminating Hallucination-Induced Errors in LLM Code Generation with Functional Clustering","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2507.22365","title":"Beyond Accuracy: How AI Metacognitive Sensitivity improves AI-assisted Decision Making","created":"2025-07-30","cited_by_count":2,"area":null},{"id":"2508.05544","title":"Conformal Sets in Multiple-Choice Question Answering under Black-Box Settings with Provable Coverage Guarantees","created":"2025-08-07","cited_by_count":2,"area":null},{"id":"2509.25989","title":"Towards Reliable and Holistic Visual In-Context Learning Prompt Selection","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2601.21003","title":"Bayesian-LoRA: Probabilistic Low-Rank Adaptation of Large Language Models","created":"2026-01-28","cited_by_count":2,"area":null},{"id":"2602.11908","title":"When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation","created":"2026-02-12","cited_by_count":2,"area":null},{"id":"2603.29693","title":"Measuring (some aspects of) the metacognition of AI","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2606.01850","title":"Does Compression Preserve Uncertainty? A Unified Benchmark for Quantized and Sparse LLMs via Conformal Prediction","created":"2026-06-01","cited_by_count":2,"area":null},{"id":"2606.27679","title":"From Signals to Transfer: A Factorised Study of Probe-Based Uncertainty Estimation in Large Language Models","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2607.20526","title":"ConfidenceBench: Evaluating Confidence Calibration in Large Language Models","created":"2026-07-10","cited_by_count":2,"area":null},{"id":"2410.02343","title":"Listening to the Wise Few: Query-Key Alignment Unlocks Latent Correct Answers in Large Language Models","created":"2024-10-03","cited_by_count":1,"area":null},{"id":"2503.05505","title":"Correctness Coverage Evaluation for Medical Multiple-Choice Question Answering Based on the Enhanced Conformal Prediction Framework","created":"2025-03-07","cited_by_count":1,"area":null},{"id":"2508.12349","title":"EgoLoc: A Generalizable Solution for Temporal Interaction Localization in Egocentric Videos","created":"2025-08-17","cited_by_count":1,"area":null},{"id":"2508.18646","title":"Beyond Benchmarks: LLM Evaluation with an Anthropomorphic and Lifecycle-oriented Roadmap","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2511.16625","title":"MedBayes-Lite: A Clinical Uncertainty Governance Layer for Risk-Aware Medical Decision Support","created":"2025-11-20","cited_by_count":1,"area":null},{"id":"2511.21860","title":"Improving Score Reliability of Multiple Choice Benchmarks with Consistency Evaluation and Altered Answer Choices","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2512.04843","title":"From Symptoms to Systems: An Expert-Guided Approach to Understanding Risks of Generative AI for Eating Disorders","created":"2025-12-04","cited_by_count":1,"area":null},{"id":"2602.02582","title":"Uncertainty and Fairness Awareness in LLM-Based Recommendation Systems","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2604.15203","title":"MADE: A Living Benchmark for Multi-Label Text Classification with Uncertainty Quantification of Medical Device Adverse Events","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2604.19530","title":"Calibrating Scientific Foundation Models with Inference-Time Stochastic Attention","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2605.08614","title":"DiagnosticIQ: A Benchmark for LLM-Based Industrial Maintenance Action Recommendation from Symbolic Rules","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2605.22864","title":"Reading Calibrated Uncertainty from Language Model Trajectories","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2605.28554","title":"High Performance, Low Reliability: Uncertainty Benchmarking for Tabular Foundation Models","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2608.25824","title":"Localize-Then-Decide Guarantees for LLM Judgments","created":"2026-08-26","cited_by_count":1,"area":null},{"id":"2609.00482","title":"Are Near-Tied LLM Rankings Robust to Family-DIF-Guided Benchmark Recomposition?","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2609.32248","title":"Anytime-Valid LLM Leaderboards via Benchmark-weighted and Block-Factorized e-Processes","created":"2026-09-26","cited_by_count":1,"area":null},{"id":"2508.02765","title":"The Architecture of Trust: A Framework for AI-Augmented Real Estate Valuation in the Era of Structured Data","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2508.10022","title":"Conformal P-Value in Multiple-Choice Question Answering Tasks with Provable Risk Control","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2511.03047","title":"Unsupervised Evaluation of Multi-Turn Objective-Driven Interactions","created":"2025-11-04","cited_by_count":0,"area":null},{"id":"2511.18359","title":"TRANSPORTER: Transferring Visual Semantics from VLM Manifolds","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2601.09522","title":"Class Adaptive Conformal Training","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2602.04572","title":"From Competition to Collaboration: Designing Sustainable Mechanisms Between LLMs and Online Forums","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2602.13264","title":"Directional Concentration Uncertainty: A representational approach to uncertainty quantification for generative models","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2602.18396","title":"Communication-Efficient Byzantine-Robust Federated Conformal Prediction via Partial Sharing","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2604.12491","title":"Calibrated Confidence Estimation for Tabular Question Answering","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.08516","title":"OracleTSC: Oracle-Informed Reward Hurdle and Uncertainty Regularization for Traffic Signal Control","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.12201","title":"Uncertainty Quantification for LLM-based Code Generation","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.19353","title":"Quantifying Aleatoric Uncertainty of In-Context Learning for Robust Measure of LLM Prediction Confidence","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2607.10855","title":"Reliability Scaling Laws for Quantized Large Language Models","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.22621","title":"Opti-Q: A Constraint-Based Optimization Framework for Multi-LLM Question Planning","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2608.27847","title":"From Uncertainty to Clinical Risk: Severity-Aware Conformal Planning for Interactive Medical Diagnosis","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2610.04239","title":"Conformal Prediction with Paraphrase-Aware Scoring for LLM Uncertainty Quantification","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}