{"total":22,"rows":[{"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":"2510.12587","title":"Teaching Language Models to Faithfully Express their Uncertainty","created":"2025-10-14","cited_by_count":7,"area":null},{"id":"2602.13540","title":"On Calibration of Large Language Models: From Response To Capability","created":"2026-02-14","cited_by_count":7,"area":null},{"id":"2602.13699","title":"Gradient-Stable Attention Heads Signal LLM Correctness","created":"2026-02-14","cited_by_count":5,"area":null},{"id":"2607.08456","title":"Two Axes of LLM Abstention: Answer Correctness and Question Answerability","created":"2026-07-09","cited_by_count":5,"area":null},{"id":"2606.11502","title":"When Role-playing, Do Models Believe What They Say?","created":"2026-06-09","cited_by_count":4,"area":null},{"id":"2603.05881","title":"Confidence Before Answering: A Paradigm Shift for Efficient LLM Uncertainty Estimation","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2604.12373","title":"Masked by Consensus: Disentangling Privileged Knowledge in LLM Correctness","created":"2026-04-14","cited_by_count":3,"area":null},{"id":"2602.06022","title":"Correctness-Optimized Residual Activation Lens (CORAL): Transferrable and Calibration-Aware Inference-Time Steering","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2604.03754","title":"Testing the Limits of Truth Directions in LLMs","created":"2026-04-04","cited_by_count":2,"area":null},{"id":"2605.09195","title":"The Geometry of Forgetting: Temporal Knowledge Drift as an Independent Axis in LLM Representations","created":"2026-05-09","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":"2607.07626","title":"Future Confidence Distillation in Large Language Models","created":"2026-07-08","cited_by_count":1,"area":null},{"id":"2607.07670","title":"Does Bielik Know What It Doesn't Know? Activation Dispersion Separates Entity Familiarity from Factual Reliability Across Model Scale","created":"2026-07-08","cited_by_count":1,"area":null},{"id":"2608.08266","title":"On the Robustness of LLMs' Internal Representation of Code Correctness","created":"2026-08-08","cited_by_count":1,"area":null},{"id":"2610.02762","title":"Dynamic LLM Routers are Often Misguided","created":"2026-10-02","cited_by_count":1,"area":null},{"id":"2602.02991","title":"Large Language Models Can Take False First Steps at Inference-time Planning","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2606.05486","title":"Localizing Prompt Ambiguity in Large Language Models with Probe-Targeted Attribution","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2607.13568","title":"Graded Entity-Familiarity Readouts in Language Models: Polish Adaptation, Cross-Language Robustness, and Refusal Steering","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2609.23999","title":"Misaligned Clinical Risk Classification and Cost Asymmetry in Open-Weight Large Language Models","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2610.06216","title":"Cross-lingual Calibration of Pre-Generation Success Probes for Multilingual LLM Routing","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.19198","title":"Embedding Geometry Shapes LLM Routing: Tracing Failure Modes and Improving Generalization","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}