{"total":58,"rows":[{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601,"area":null},{"id":"2310.06824","title":"The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets","created":"2023-10-10","cited_by_count":712,"area":null},{"id":"2311.08298","title":"A Survey of Confidence Estimation and Calibration in Large Language Models","created":"2023-11-14","cited_by_count":256,"area":null},{"id":"2410.02707","title":"LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations","created":"2024-10-03","cited_by_count":244,"area":null},{"id":"2308.14752","title":"AI Deception: A Survey of Examples, Risks, and Potential Solutions","created":"2023-08-28","cited_by_count":188,"area":null},{"id":"2407.12831","title":"Truth is Universal: Robust Detection of Lies in LLMs","created":"2024-07-03","cited_by_count":79,"area":null},{"id":"2506.10805","title":"Detecting High-Stakes Interactions with Activation Probes","created":"2025-06-12","cited_by_count":53,"area":null},{"id":"2312.01350","title":"Honesty Is the Best Policy: Defining and Mitigating AI Deception","created":"2023-12-03","cited_by_count":40,"area":null},{"id":"2312.10029","title":"Challenges with unsupervised LLM knowledge discovery","created":"2023-12-15","cited_by_count":31,"area":null},{"id":"2405.21030","title":"Standards for Belief Representations in LLMs","created":"2024-05-31","cited_by_count":30,"area":null},{"id":"2412.01784","title":"Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models","created":"2024-12-02","cited_by_count":24,"area":null},{"id":"2403.15115","title":"Language Models in Dialogue: Conversational Maxims for Human-AI Interactions","created":"2024-03-22","cited_by_count":21,"area":null},{"id":"2312.02798","title":"Weakly Supervised Detection of Hallucinations in LLM Activations","created":"2023-12-05","cited_by_count":20,"area":null},{"id":"2404.09971","title":"Constructing Benchmarks and Interventions for Combating Hallucinations in LLMs","created":"2024-04-15","cited_by_count":19,"area":null},{"id":"2507.12691","title":"Benchmarking Deception Probes via Black-to-White Performance Boosts","created":"2025-07-16","cited_by_count":19,"area":null},{"id":"2506.00823","title":"Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks","created":"2025-06-01","cited_by_count":18,"area":null},{"id":"2407.11015","title":"Does ChatGPT Have a Mind?","created":"2024-06-27","cited_by_count":14,"area":null},{"id":"2410.22071","title":"Distinguishing Ignorance from Error in LLM Hallucinations","created":"2024-10-29","cited_by_count":14,"area":null},{"id":"2511.22662","title":"Difficulties with Evaluating a Deception Detector for AIs","created":"2025-11-27","cited_by_count":13,"area":null},{"id":"2401.04854","title":"Are Language Models More Like Libraries or Like Librarians? Bibliotechnism, the Novel Reference Problem, and the Attitudes of LLMs","created":"2024-01-10","cited_by_count":11,"area":null},{"id":"2601.20834","title":"Linear representations in language models can change dramatically over a conversation","created":"2026-01-28","cited_by_count":10,"area":null},{"id":"2505.19240","title":"LLLMs: A Data-Driven Survey of Evolving Research on Limitations of Large Language Models","created":"2025-05-25","cited_by_count":9,"area":null},{"id":"2506.08572","title":"The Geometries of Truth Are Orthogonal Across Tasks","created":"2025-06-10","cited_by_count":9,"area":null},{"id":"2510.11905","title":"LLM Knowledge is Brittle: Truthfulness Representations Rely on Superficial Resemblance","created":"2025-10-13","cited_by_count":9,"area":null},{"id":"2511.17408","title":"The Impact of Off-Policy Training Data on Probe Generalisation","created":"2025-11-21","cited_by_count":9,"area":null},{"id":"2411.04847","title":"Prompt-Guided Internal States for Hallucination Detection of Large Language Models","created":"2024-11-07","cited_by_count":8,"area":null},{"id":"2507.08017","title":"Mechanistic Indicators of Understanding in Large Language Models","created":"2025-07-07","cited_by_count":8,"area":null},{"id":"2602.20273","title":"The Truthfulness Spectrum Hypothesis","created":"2026-02-23","cited_by_count":8,"area":null},{"id":"2404.18865","title":"Truth-value judgment in language models: 'truth directions' are context sensitive","created":"2024-04-29","cited_by_count":7,"area":null},{"id":"2606.07612","title":"Position: Anthropomorphic Misalignment Research Needs Stronger Evidence","created":"2026-05-29","cited_by_count":7,"area":null},{"id":"2505.16170","title":"When Do LLMs Admit Their Mistakes? Understanding The Role Of Model Belief In Retraction","created":"2025-05-22","cited_by_count":6,"area":null},{"id":"2506.00088","title":"HD-NDEs: Neural Differential Equations for Hallucination Detection in LLMs","created":"2025-05-30","cited_by_count":6,"area":null},{"id":"2405.12999","title":"An Assessment of Model-On-Model Deception","created":"2024-05-10","cited_by_count":5,"area":null},{"id":"2410.02472","title":"Meta-Models: An Architecture for Decoding LLM Behaviors Through Interpreted Embeddings and Natural Language","created":"2024-10-03","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":"2509.19372","title":"Representation-based Broad Hallucination Detectors Fail to Generalize Out of Distribution","created":"2025-09-19","cited_by_count":4,"area":null},{"id":"2501.15054","title":"Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models","created":"2025-01-25","cited_by_count":3,"area":null},{"id":"2602.02467","title":"Indications of Belief-Guided Agency and Meta-Cognitive Monitoring in Large Language Models","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2410.16645","title":"Chatting with Bots: AI, Speech Acts, and the Edge of Assertion","created":"2024-10-22","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":"2608.03035","title":"Language Models Encode the Contextual Truth of Propositions","created":"2026-08-04","cited_by_count":2,"area":null},{"id":"2407.12846","title":"Identifying the Source of Generation for Large Language Models","created":"2024-07-05","cited_by_count":1,"area":null},{"id":"2412.07965","title":"HalluCana: Fixing LLM Hallucination with A Canary Lookahead","created":"2024-12-10","cited_by_count":1,"area":null},{"id":"2505.09807","title":"Exploring the generalization of LLM truth directions on conversational formats","created":"2025-05-14","cited_by_count":1,"area":null},{"id":"2604.11662","title":"A Robust Evaluation of Probe Robustness: Lessons for Reliable OOD Uncertainty Quantification","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2606.12268","title":"The Impossibility of Eliciting Latent Knowledge","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2608.28930","title":"The Hallucination Signal Is a Mean Shift: Why Simple Probes Suffice","created":"2026-08-28","cited_by_count":1,"area":null},{"id":"2410.04272","title":"Evaluating Language Model Character Traits","created":"2024-10-05","cited_by_count":0,"area":null},{"id":"2501.00885","title":"Representation in large language models","created":"2025-01-01","cited_by_count":0,"area":null},{"id":"2507.22197","title":"Explainability Through Systematicity: The Hard Systematicity Challenge for Artificial Intelligence","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2511.02089","title":"LLM Probing with Contrastive Eigenproblems: Improving Understanding and Applicability of CCS","created":"2025-11-03","cited_by_count":0,"area":null},{"id":"2603.10003","title":"Probing the Limits of the Lie Detector Approach to LLM Deception","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2605.14449","title":"When Answers Stray from Questions: Hallucination Detection via Question-Answer Orthogonal Decomposition","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2607.11945","title":"Belief-reality separation lives in routing over a shared value slot in language models","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2608.29109","title":"Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2609.04409","title":"A Systematic Evaluation of Cross-Lingual Consistency Enhancement Methods in Multilingual Language Models","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.15407","title":"Can AI systems have free will?","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.39807","title":"Stress-Testing LLM Lie Detectors: Role-Play Failures and Spurious Correlations","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}