{"total":82,"rows":[{"id":"2509.03730","title":"The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs","created":"2025-09-03","cited_by_count":36,"area":null},{"id":"2502.09083","title":"Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checking","created":"2025-02-13","cited_by_count":29,"area":null},{"id":"2603.17839","title":"How do LLMs Compute Verbal Confidence","created":"2026-03-18","cited_by_count":26,"area":null},{"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":"2506.10150","title":"When Large Language Models are Reliable for Judging Empathic Communication","created":"2025-06-11","cited_by_count":21,"area":null},{"id":"2505.24858","title":"MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs","created":"2025-05-30","cited_by_count":16,"area":null},{"id":"2407.15814","title":"Perceptions of Linguistic Uncertainty by Language Models and Humans","created":"2024-07-22","cited_by_count":15,"area":null},{"id":"2507.10587","title":"Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missing","created":"2025-07-11","cited_by_count":14,"area":null},{"id":"2405.15185","title":"An Evaluation of Estimative Uncertainty in Large Language Models","created":"2024-05-24","cited_by_count":13,"area":null},{"id":"2502.15620","title":"Paradigms of AI Evaluation: Mapping Goals, Methodologies and Culture","created":"2025-02-21","cited_by_count":11,"area":null},{"id":"2507.19364","title":"From the Fluency Fallacy to the Micro-to-Macro Validity Gap: Opportunities and Pitfalls of LLMs in Social Simulation","created":"2025-07-25","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":"2502.11919","title":"From Text to Trust: Empowering AI-assisted Decision Making with Adaptive LLM-powered Analysis","created":"2025-02-17","cited_by_count":9,"area":null},{"id":"2507.03120","title":"How Overconfidence in Initial Choices and Underconfidence Under Criticism Modulate Change of Mind in Large Language Models","created":"2025-07-03","cited_by_count":9,"area":null},{"id":"2505.21740","title":"Counterfactual Simulatability of LLM Explanations for Generation Tasks","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2502.14445","title":"PredictaBoard: Benchmarking LLM Score Predictability","created":"2025-02-20","cited_by_count":7,"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":"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":"2504.10979","title":"Deep Learning in Concealed Dense Prediction","created":"2025-04-15","cited_by_count":6,"area":null},{"id":"2510.00857","title":"ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2504.03579","title":"Hallucination Detection on a Budget: Efficient Bayesian Estimation of Semantic Entropy","created":"2025-04-04","cited_by_count":5,"area":null},{"id":"2605.01428","title":"Hallucinations Undermine Trust; Metacognition is a Way Forward","created":"2026-05-02","cited_by_count":5,"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":"2510.05126","title":"Generalization of Fine-Tuned Uncertainty Communication and Metacognition in Large Language Models","created":"2025-09-30","cited_by_count":4,"area":null},{"id":"2601.10645","title":"Influential Training Data Retrieval for Explaining Verbalized Confidence of LLMs","created":"2026-01-15","cited_by_count":4,"area":null},{"id":"2501.09127","title":"Multilingual LLMs Struggle to Link Orthography and Semantics in Bilingual Word Processing","created":"2025-01-15","cited_by_count":3,"area":null},{"id":"2602.05883","title":"A Guide to Large Language Models in Modeling and Simulation: From Core Techniques to Critical Challenges","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2604.22271","title":"How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals","created":"2026-04-24","cited_by_count":3,"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":"2512.09088","title":"Calibrated Trust in Dealing with LLM Hallucinations: A Qualitative Study","created":"2025-12-09","cited_by_count":2,"area":null},{"id":"2512.10451","title":"Metacognitive Sensitivity for Test-Time Dynamic Model Selection","created":"2025-12-11","cited_by_count":2,"area":null},{"id":"2601.05905","title":"Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2602.04003","title":"When AI Persuades: Adversarial Explanation Attacks on Human Trust in AI-Assisted Decision Making","created":"2026-02-03","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":"2604.01206","title":"RELISH: LLM REgression with a Latent Iterative State Head","created":"2026-04-01","cited_by_count":2,"area":null},{"id":"2605.28778","title":"Can LLMs Use Linguistic Uncertainty Markers to Reliably Reflect Intrinsic Confidence?","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2408.08083","title":"Confidence-weighted integration of human and machine judgments for superior decision-making","created":"2024-08-15","cited_by_count":1,"area":null},{"id":"2505.17855","title":"Explaining Sources of Uncertainty in Automated Fact-Checking","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2508.07390","title":"Urbanite: A Dataflow-Based Framework for Human-AI Interactive Alignment in Urban Visual Analytics","created":"2025-08-10","cited_by_count":1,"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":"2511.07669","title":"Making LLMs Reliable When It Matters Most: A Five-Layer Architecture for High-Stakes Decisions","created":"2025-11-10","cited_by_count":1,"area":null},{"id":"2512.16750","title":"Plausibility as Failure: How LLMs and Humans Co-Construct Epistemic Error","created":"2025-12-18","cited_by_count":1,"area":null},{"id":"2602.20104","title":"Align When They Want, Complement When They Need! Human-Centered Ensembles for Adaptive Human-AI Collaboration","created":"2026-02-23","cited_by_count":1,"area":null},{"id":"2603.20229","title":"Characterizing the ability of LLMs to recapitulate Americans' distributional responses to public opinion polling questions across political issues","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2603.22152","title":"More Isn't Always Better: Balancing Decision Accuracy and Conformity Pressures in Multi-AI Advice","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2604.20048","title":"Culturally uneven urban perception in large language models","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2605.22975","title":"When AI Takes Sides on Questions of Faith: Persistent Asymmetries in AI-Mediated Faith Guidance","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2606.29034","title":"The strength of clinical evidence is recoverable from language model representations but not from their stated grades","created":"2026-06-27","cited_by_count":1,"area":null},{"id":"2607.11881","title":"Metacognition in LLMs: Foundations, Progress, and Opportunities","created":"2026-07-13","cited_by_count":1,"area":null},{"id":"2607.19355","title":"Information Discernment in Large Language Models","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2607.20446","title":"Distinguishing Artificial from Authentic: Evaluating LLMs for Detecting LLM-Generated Content","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2608.26327","title":"How Unlikely Is \"Unlikely\"? Assessing Verbal Probability Perception Across Large Language Models","created":"2026-08-26","cited_by_count":1,"area":null},{"id":"2609.26489","title":"Calibration as a First-Class Criterion in LLM Evaluation","created":"2026-09-22","cited_by_count":1,"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":"2510.17764","title":"Evaluating Medical LLMs by Levels of Autonomy: A Survey Moving from Benchmarks to Applications","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2511.11773","title":"On the Measure of a Model: From Intelligence to Generality","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2601.21650","title":"When Life Gives You AI, Will You Turn It Into A Market for Lemons? Understanding How Information Asymmetries About AI System Capabilities Affect Market Outcomes and Adoption","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.11924","title":"Who Does What? Archetypes of Roles Assigned to LLMs During Human-AI Decision-Making","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.09985","title":"The Dunning-Kruger Effect in Large Language Models: An Empirical Study of Confidence Calibration","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.22299","title":"Between the Layers Lies the Truth: Uncertainty Estimation in LLMs Using Intra-Layer Local Information Scores","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2603.29681","title":"Beyond the Steeper Curve: AI-Mediated Metacognitive Decoupling and the Limits of the Dunning-Kruger Metaphor","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.07398","title":"Breaking the Illusion of Identity in LLM Tooling","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2604.16845","title":"DART: Mitigating Harm Drift in Difference-Aware LLMs via Distill-Audit-Repair Training","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2604.22764","title":"Implicit Humanization in Everyday LLM Moral Judgments","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2604.25639","title":"Large language models eroding science understanding: an empirical study of malignment","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.05777","title":"Estimating the Black-box LLM Uncertainty with Distribution-Aligned Adversarial Distillation","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.23867","title":"Human Decision-Making with Persuasive and Narrative LLM Explanations","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2605.30675","title":"Human-Alignment, Calibration, and Activation Patterns in Large Language Model Uncertainty","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.07951","title":"From 'May' to 'Is': Certainty Distortion in Language Model Rewriting","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2607.02510","title":"Online Safety Monitoring for LLMs","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.05123","title":"ASSEMCAD: Production-Ready CAD Assembly Generation from Natural Language","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.20454","title":"Response drift across frontier large language models","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2608.09080","title":"When Confidence Fails: Overconfidence in LLMs under Uncertainty and Missing Clinical Information","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.19083","title":"When Readability and Source Retention Diverge: An Evaluability Gap in AI Translation","created":"2026-08-19","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":"2609.31245","title":"RupeeBias: Auditing Demographic Bias in Indian Economic Guidance from Large Language Models","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.33886","title":"LLMs learn different forms of metacognition when trained to predict their own accuracy","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.34158","title":"Toward a Graded Measure of Belief Stability in Large Language Models","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38797","title":"Evaluating Persistent Calibration under Evolving Model Knowledge","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39518","title":"Referential Uncertainty in Human--AI Collaboration","created":"2026-09-30","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},{"id":"2610.02378","title":"THPL: A Vision-to-Language Decision Support Framework for Rainbow Trout Feeding Management in RAS","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}