{"total":95,"rows":[{"id":"2509.18970","title":"LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions","created":"2025-09-23","cited_by_count":50,"area":"agents"},{"id":"2510.10649","title":"Unlocking Exploration in RLVR: Uncertainty-aware Advantage Shaping for Deeper Reasoning","created":"2025-10-12","cited_by_count":34,"area":"lr"},{"id":"2510.01180","title":"BroRL: Scaling Reinforcement Learning via Broadened Exploration","created":"2025-10-01","cited_by_count":25,"area":"lr"},{"id":"2505.11737","title":"TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning","created":"2025-05-16","cited_by_count":24,"area":"lr"},{"id":"2504.14045","title":"Metacognition and Uncertainty Communication in Humans and Large Language Models","created":"2025-04-18","cited_by_count":23,"area":null},{"id":"2505.23854","title":"Revisiting Uncertainty Estimation and Calibration of Large Language Models","created":"2025-05-29","cited_by_count":23,"area":"moe"},{"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":"2602.11865","title":"Intelligent AI Delegation","created":"2026-02-12","cited_by_count":18,"area":null},{"id":"2511.04418","title":"The Illusion of Certainty: Uncertainty Quantification for LLMs Fails under Ambiguity","created":"2025-11-06","cited_by_count":17,"area":null},{"id":"2509.13813","title":"Geometric Uncertainty for Detecting and Correcting Hallucinations in LLMs","created":"2025-09-17","cited_by_count":13,"area":null},{"id":"2504.11101","title":"Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self-Improving OCR","created":"2025-04-15","cited_by_count":12,"area":"mllm"},{"id":"2510.16492","title":"Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safety","created":"2025-10-18","cited_by_count":12,"area":"agents"},{"id":"2509.04492","title":"Learned Hallucination Detection in Black-Box LLMs using Token-level Entropy Production Rate","created":"2025-09-01","cited_by_count":10,"area":null},{"id":"2509.16330","title":"Generalizability of Large Language Model-Based Agents: A Comprehensive Survey","created":"2025-09-19","cited_by_count":10,"area":"agents"},{"id":"2604.06543","title":"The Illusion of Stochasticity in LLMs","created":"2026-04-08","cited_by_count":9,"area":null},{"id":"2509.14478","title":"Estimating Semantic Alphabet Size for LLM Uncertainty Quantification","created":"2025-09-17","cited_by_count":8,"area":null},{"id":"2512.01556","title":"LEC: Linear Expectation Constraints for Selection-Conditioned Risk Control in Selective Prediction and Routing Systems","created":"2025-12-01","cited_by_count":7,"area":null},{"id":"2603.14893","title":"LLMs as Signal Detectors: Sensitivity, Bias, and the Temperature-Criterion Analogy","created":"2026-03-16","cited_by_count":7,"area":null},{"id":"2510.11483","title":"Uncertainty Quantification for Retrieval-Augmented Reasoning","created":"2025-10-13","cited_by_count":6,"area":"lr"},{"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":"2604.02543","title":"Overconfidence and Calibration in Medical VQA: Empirical Findings and Hallucination-Aware Mitigation","created":"2026-04-02","cited_by_count":6,"area":"mllm"},{"id":"2505.19145","title":"Do Large Language Models (Really) Need Statistical Foundations?","created":"2025-05-25","cited_by_count":5,"area":null},{"id":"2511.13240","title":"Knowing What You Know Is Not Enough: Large Language Model Confidences Don't Align With Their Actions","created":"2025-11-17","cited_by_count":4,"area":"agents"},{"id":"2602.04577","title":"Semantic Self-Distillation for Language Model Uncertainty","created":"2026-02-04","cited_by_count":4,"area":"distill"},{"id":"2508.14357","title":"Organ-Agents: Virtual Human Physiology Simulator via LLMs","created":"2025-08-20","cited_by_count":3,"area":"agents"},{"id":"2601.21500","title":"Task-Awareness Improves LLM Generations and Uncertainty","created":"2026-01-29","cited_by_count":3,"area":null},{"id":"2602.12996","title":"Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language Models","created":"2026-02-13","cited_by_count":3,"area":null},{"id":"2603.18014","title":"Real-Time Trustworthiness Scoring for LLM Structured Outputs and Data Extraction","created":"2026-02-24","cited_by_count":3,"area":null},{"id":"2605.09537","title":"Drift is a Sampling Error: SNR-Aware Power Distributions for Long-Horizon Robotic Planning","created":"2026-05-10","cited_by_count":3,"area":"vla"},{"id":"2605.17304","title":"Compress the Context, Keep the Commitments: A Formal Framework for Verifiable LLM Context Compression","created":"2026-05-17","cited_by_count":3,"area":"inference"},{"id":"2605.23414","title":"When Planning Fails Despite Correct Execution: On Epistemic Calibration for LLM-Based Multi-Agent Systems","created":"2026-05-22","cited_by_count":3,"area":"agents"},{"id":"2506.01116","title":"ChemAU: Harness the Reasoning of LLMs in Chemical Research with Adaptive Uncertainty Estimation","created":"2025-06-01","cited_by_count":2,"area":"lr"},{"id":"2509.17192","title":"Shall We Play a Game? Language Models for Open-ended Wargames","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2509.18864","title":"Conf-Profile: A Confidence-Driven Reasoning Paradigm for Label-Free User Profiling","created":"2025-09-23","cited_by_count":2,"area":"lr"},{"id":"2512.08810","title":"Multicalibration for LLM-based Code Generation","created":"2025-12-09","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":"2603.26539","title":"How Open Must Language Models be to Enable Reliable Scientific Inference?","created":"2026-03-27","cited_by_count":2,"area":null},{"id":"2604.23333","title":"Process Supervision of Confidence Margin for Calibrated LLM Reasoning","created":"2026-04-25","cited_by_count":2,"area":"lr"},{"id":"2605.19228","title":"Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution","created":"2026-05-19","cited_by_count":2,"area":"lr"},{"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":"2606.19868","title":"A Systematic Evaluation of Black-Box Uncertainty Estimation Methods for Large Language Models","created":"2026-06-18","cited_by_count":2,"area":null},{"id":"2606.29184","title":"BaRA: Bayesian Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning","created":"2026-06-28","cited_by_count":2,"area":null},{"id":"2607.04034","title":"The \"I Don't Know\" Filter: Enhancing Agentic Reliability in Function Calling","created":"2026-07-04","cited_by_count":2,"area":"agents"},{"id":"2607.20526","title":"ConfidenceBench: Evaluating Confidence Calibration in Large Language Models","created":"2026-07-10","cited_by_count":2,"area":null},{"id":"2505.10143","title":"GE-Chat: A Graph Enhanced RAG Framework for Evidential Response Generation of LLMs","created":"2025-05-15","cited_by_count":1,"area":"rag"},{"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":"2507.02256","title":"Uncertainty-aware Reward Design Process","created":"2025-07-03","cited_by_count":1,"area":"lr"},{"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":"2512.02625","title":"CryptoQA: A Large-scale Question-answering Dataset for AI-assisted Cryptography","created":"2025-12-02","cited_by_count":1,"area":null},{"id":"2601.01862","title":"Judging with Personality and Confidence: A Study on Personality-Conditioned LLM Relevance Assessment","created":"2026-01-05","cited_by_count":1,"area":null},{"id":"2602.08520","title":"Reinforcement Inference: Leveraging Uncertainty for Self-Correcting Language Model Reasoning","created":"2026-02-09","cited_by_count":1,"area":"lr"},{"id":"2602.23546","title":"Humans and LLMs Diverge on Probabilistic Inferences","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2605.04764","title":"Elicitation Matters: How Prompts and Query Protocols Shape LLM Surrogates under Sparse Observations","created":"2026-05-06","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":"2605.22949","title":"MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination","created":"2026-05-21","cited_by_count":1,"area":"agents"},{"id":"2606.07017","title":"The Sim-to-Real Gap of Foundation Model Agents: A Unified MDP Perspective","created":"2026-06-05","cited_by_count":1,"area":"agents"},{"id":"2606.20662","title":"Confidence Laundering in Agent Systems: Why Uncertainty Needs a Latent Carrier","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2609.04486","title":"Uncertainty Signals for Network Intent Translation: Risk Ranking and Ambiguity Localization","created":"2026-09-03","cited_by_count":1,"area":null},{"id":"2507.15174","title":"Joint-Local Grounded Action Transformation for Sim-to-Real Transfer in Multi-Agent Traffic Control","created":"2025-07-21","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":"2512.05461","title":"Knowing Your Uncertainty -- On the application of LLM in social sciences","created":"2025-12-05","cited_by_count":0,"area":null},{"id":"2601.02574","title":"Fact-Checking with Large Language Models via Probabilistic Certainty and Consistency","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2601.15645","title":"Towards Reliable Medical LLMs: Benchmarking and Enhancing Confidence Estimation of Large Language Models in Medical Consultation","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2602.10816","title":"Beyond Confidence: The Rhythms of Reasoning in Generative Models","created":"2026-02-11","cited_by_count":0,"area":"lr"},{"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":"2603.23853","title":"SCoOP: Semantic Consistent Opinion Pooling for Uncertainty Quantification in Multiple Vision-Language Model Systems","created":"2026-03-25","cited_by_count":0,"area":"lr"},{"id":"2603.26363","title":"A Formal Framework for Uncertainty Analysis of Text Generation with Large Language Models","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2604.01652","title":"ThinknCheck: Grounded Claim Verification with Compact, Reasoning-Driven, and Interpretable Models","created":"2026-04-02","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":"2604.05757","title":"Identifying Influential N-grams in Confidence Calibration via Regression Analysis","created":"2026-04-07","cited_by_count":0,"area":"lr"},{"id":"2604.19162","title":"Mind the Unseen Mass: Unmasking LLM Hallucinations via Soft-Hybrid Alphabet Estimation","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.02010","title":"Reliable AI Needs to Externalize Implicit Knowledge: A Human-AI Collaboration Perspective","created":"2026-05-03","cited_by_count":0,"area":null},{"id":"2605.06919","title":"Can LLMs Take Retrieved Information with a Grain of Salt?","created":"2026-05-07","cited_by_count":0,"area":"rag"},{"id":"2605.11235","title":"Internalizing Curriculum Judgment for LLM Reinforcement Fine-Tuning","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.11328","title":"Epistemic Uncertainty for Test-Time Discovery","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":"2605.15421","title":"U-SEG: Uncertainty in SEGmentation -- A systematic multi-variable exploration","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.17508","title":"BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregation","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2605.19220","title":"Position: Uncertainty Quantification in LLMs is Just Unsupervised Clustering","created":"2026-05-19","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":"2605.28170","title":"Localizing Input Uncertainty Quantification for Large Language Models via Shapley Values","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2605.29956","title":"Uncertainty Quantification for Multimodal Retrieval Augmented Generation","created":"2026-05-28","cited_by_count":0,"area":"mllm"},{"id":"2607.08017","title":"Can We Trust LLM's Logic? Quantifying Uncertainty, Coherence, and Robustness via a Graph-Based Framework","created":"2026-07-09","cited_by_count":0,"area":"lr"},{"id":"2607.20712","title":"Evaluating Large Language Models for Symbolic Security Protocol Analysis","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2607.22951","title":"Modeling Memory-Dependent Reliability of LLMs: A Hidden Markov Model","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2607.28617","title":"AISPA: User-Centric System Prompt Auditing for Large Language Model Applications","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.02553","title":"A Taxonomy of Cognitive Capability Gaps in Generative and Agentic AI","created":"2026-08-03","cited_by_count":0,"area":"agents"},{"id":"2608.05616","title":"TruthLens: Object Hallucination Detection via Self-Evaluating Truthfulness Scores in LVLMs","created":"2026-08-06","cited_by_count":0,"area":"mllm"},{"id":"2608.17084","title":"Uncertainty-Aware Decision Making in Multimodal Large Language Models","created":"2026-08-17","cited_by_count":0,"area":"mllm"},{"id":"2609.00652","title":"Self-Reports Are Not Verification: Environment-Grounded Auditing of LLM Operators in Evolutionary Search","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.05284","title":"GUT: Quantifying and Optimizing the Reasoning Uncertainty of LLMs via Graph Complexity","created":"2026-09-04","cited_by_count":0,"area":"lr"},{"id":"2609.07395","title":"Uncertainty Quantification for LLM Agents: A Taxonomy, an Evaluation Protocol, and an Empirical Study","created":"2026-09-07","cited_by_count":0,"area":"agents"},{"id":"2609.32470","title":"On the Pitfalls of Verbalized Confidence Priors for Calibrating Large Reasoning Models","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2610.14365","title":"ConformalGuard: False-Positive-Controlled Action Gating for LM Classifiers","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.20328","title":"Argument Graph Uncertainty: Quantifying Uncertainty from the Logical Structure of Reasoning Chains","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}