{"total":69,"rows":[{"id":"2509.25760","title":"TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning","created":"2025-09-30","cited_by_count":27,"area":null},{"id":"2409.17213","title":"Plurals: A System for Guiding LLMs Via Simulated Social Ensembles","created":"2024-09-25","cited_by_count":17,"area":null},{"id":"2412.06748","title":"Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models","created":"2024-12-09","cited_by_count":14,"area":null},{"id":"2503.14481","title":"Don't lie to your friends: Learning what you know from collaborative self-play","created":"2025-03-18","cited_by_count":14,"area":null},{"id":"2506.09669","title":"Query-Level Uncertainty in Large Language Models","created":"2025-06-11","cited_by_count":14,"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":"2410.17234","title":"Fine-Tuning Large Language Models to Appropriately Abstain with Semantic Entropy","created":"2024-10-22","cited_by_count":11,"area":null},{"id":"2511.04962","title":"Too Good to be Bad: On the Failure of LLMs to Role-Play Villains","created":"2025-11-07","cited_by_count":11,"area":null},{"id":"2601.05503","title":"Over-Searching in Search-Augmented Large Language Models","created":"2026-01-09","cited_by_count":11,"area":null},{"id":"2511.21322","title":"TALES: A Taxonomy and Analysis of Cultural Representations in LLM-generated Stories","created":"2025-11-26","cited_by_count":10,"area":null},{"id":"2512.24661","title":"Do Large Language Models Know What They Are Capable Of?","created":"2025-12-31","cited_by_count":10,"area":null},{"id":"2603.22161","title":"Causal Evidence that Language Models use Confidence to Drive Behavior","created":"2026-03-23","cited_by_count":10,"area":null},{"id":"2602.04755","title":"When Silence Is Golden: Can LLMs Learn to Abstain in Temporal QA and Beyond?","created":"2026-02-04","cited_by_count":7,"area":null},{"id":"2511.11500","title":"Honesty over Accuracy: Trustworthy Language Models through Reinforced Hesitation","created":"2025-11-14","cited_by_count":5,"area":null},{"id":"2604.27914","title":"Geometry-Calibrated Conformal Abstention for Language Models","created":"2026-04-30","cited_by_count":5,"area":null},{"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":"2506.00694","title":"Measuring Faithfulness and Abstention: An Automated Pipeline for Evaluating LLM-Generated 3-ply Case-Based Legal Arguments","created":"2025-05-31","cited_by_count":3,"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":"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":"2604.25149","title":"Semantic Layers for Reliable LLM-Powered Data Analytics: A Paired Benchmark of Accuracy and Hallucination Across Three Frontier Models","created":"2026-04-28","cited_by_count":3,"area":null},{"id":"2503.23687","title":"MKA: Leveraging Cross-Lingual Consensus for Model Abstention","created":"2025-03-31","cited_by_count":2,"area":null},{"id":"2510.01255","title":"Longitudinal Monitoring of LLM Content Moderation of Social Issues","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2602.00906","title":"Hallucination is a Consequence of Space-Optimality: A Rate-Distortion Theorem for Membership Testing","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2602.02605","title":"Fine-Tuning Language Models to Know What They Know","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2605.20098","title":"Neurosymbolic Learning for Inference-Time Argumentation","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2606.11105","title":"PhantomBench: Benchmarking the Non-existential Threat of Language Models","created":"2026-06-09","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":"2608.17994","title":"Judge, Retrieve, or Abstain: Uncertainty-Guarded LLM Judging with Provable Risk Guarantees","created":"2026-08-18","cited_by_count":2,"area":null},{"id":"2509.07309","title":"PIE: Performance Interval Estimation for Free-Form Generation Tasks","created":"2025-09-09","cited_by_count":1,"area":null},{"id":"2601.22648","title":"UCPO: Uncertainty-Aware Policy Optimization","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2604.13201","title":"InfiniteScienceGym: An Unbounded, Procedurally-Generated Benchmark for Scientific Analysis","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2604.17843","title":"Learning from AVA: Early Lessons from a Curated and Trustworthy Generative AI for Policy and Development Research","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2605.05626","title":"When2Speak: A Dataset for Temporal Participation and Turn-Taking in Multi-Party Conversations for Large Language Models","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2606.00251","title":"Capability Self-Assessment in Large Language Models","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.22179","title":"The Score Granularity Gap in Black-Box LLM Classification: A Comparative Study of Confidence Constructions","created":"2026-06-20","cited_by_count":1,"area":null},{"id":"2606.32012","title":"CoMet: Context and Multiplicity Decomposition for Multimodal Uncertainty Estimation","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2607.14399","title":"Instrument Effects in Language-Model Honesty Evaluation: An Auditable Single-System Demonstration","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2607.20492","title":"PhantomFill: When the Form Demands an Answer, Language Models Invent One","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2608.10008","title":"Do LLM Recommenders Know When They're Hallucinating? Auditing Confidence Calibration in Catalog Faithfulness","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2510.03527","title":"Sample, Align, Synthesize: Graph-Based Response Synthesis with ConGrs","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2510.14925","title":"False Fixed Points: Kantian Feedback, Stable Miscalibration, and Representational Compression in LLMs","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2511.06073","title":"Stemming Hallucination in Language Models Using a Licensing Oracle","created":"2025-11-08","cited_by_count":0,"area":null},{"id":"2512.21238","title":"Assessing the Software Security Comprehension of Large Language Models","created":"2025-12-24","cited_by_count":0,"area":null},{"id":"2603.00350","title":"Monotropic Artificial Intelligence: Toward a Cognitive Taxonomy of Domain-Specialized Language Models","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2603.17504","title":"Inducing Epistemological Humility in Large Language Models: A Targeted SFT Approach to Reducing Hallucination","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2604.24801","title":"Architecture Determines Observability of Transformers","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.06673","title":"Domain-level metacognitive monitoring in frontier LLMs: A 33-model atlas","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.07919","title":"MedVIGIL: Evaluating Trustworthy Medical VLMs Under Broken Visual Evidence","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.14744","title":"Mechanical Enforcement for LLM Governance:Evidence of Governance-Task Decoupling in Financial Decision Systems","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.16272","title":"Beyond Compliance: How AI Could Help Creative Writers by Refusing Them","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2605.17029","title":"Task Abstention for Large Language Models in Code Generation","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2606.26101","title":"Know2Guess: A Contamination-Aware Multi-Zone Benchmark for Knowledge-Boundary Evaluation in Large Language Models","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2606.27383","title":"CalBrief: A Pilot Diagnostic Benchmark for Evidence-Calibrated Scientific Briefing with Large Language Models","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2607.05985","title":"Auto-DSM Under the Lens: A Black-Box Evaluation Framework for LLM-Based DSM Generation","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2608.09187","title":"Failure-Aware Long-Form Translation: Design and Implementation of a Recoverable LLM Translation System","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.13591","title":"Stable Miscalibration in Large Language Models: A Practical View of High-Confidence Errors","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2608.23507","title":"When Names Cross Scripts: A Source-Grounded Benchmark for Historical Entity Reconciliation in the Mongol World","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.23568","title":"RENDER: Controlling Reader-Facing Evidence in LLM Memory Evaluation","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2608.27716","title":"PCFBench: A Diagnostic Benchmark for Product Carbon Footprint Estimation","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.02771","title":"From Reweighting to Rewriting: Unlocking the Intervention Effects of Influential Samples in Training Data Attribution","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.10724","title":"Finishing the Task Is Not Enough: Evaluating Agent Resilience and Considerate Participation under Accumulating Challenge","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.10728","title":"Towards a Deterministic Math Solver for Clinical Language Models","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.22934","title":"Measuring Behavioural Signatures of Large Language Models through Psychometric Profiling","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.26035","title":"Truth for Believable AI: Expressed Doubt, Provenance, and Belief Revision as an Engineerable Stance","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.30219","title":"Requirement-Bound Verified Commissioning: A Frozen Four-Billion-Parameter Local Model as a Candidate Generator under an External Acceptance Layer with Verification and Release Authority","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.32269","title":"Before Answering: Evidence Sufficiency under Size-Matched Memory Construction","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.09446","title":"Arctic Questions, Missing Answers: A Dataset and Benchmark for LLM Abstention in Arctic Science","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.16318","title":"Strong yet Controllable LLM Abstention without Learning to Abstain","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.18498","title":"Aligning Faithfulness for Theory-Scale Autoformalization","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}