{"total":83,"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":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916,"area":null},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467,"area":"alignment"},{"id":"2503.11926","title":"Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation","created":"2025-03-14","cited_by_count":384,"area":"lr"},{"id":"2310.20624","title":"LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B","created":"2023-10-31","cited_by_count":195,"area":"alignment"},{"id":"2311.07590","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","created":"2023-11-09","cited_by_count":146,"area":null},{"id":"2406.07358","title":"AI Sandbagging: Language Models can Strategically Underperform on Evaluations","created":"2024-06-11","cited_by_count":145,"area":null},{"id":"2511.18397","title":"Natural Emergent Misalignment from Reward Hacking in Production RL","created":"2025-11-23","cited_by_count":136,"area":"alignment"},{"id":"2412.05563","title":"A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions","created":"2024-12-07","cited_by_count":121,"area":null},{"id":"2410.13787","title":"Looking Inward: Language Models Can Learn About Themselves by Introspection","created":"2024-10-17","cited_by_count":113,"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":"2312.07000","title":"Alignment for Honesty","created":"2023-12-12","cited_by_count":74,"area":"alignment"},{"id":"2403.05973","title":"Calibrating Large Language Models Using Their Generations Only","created":"2024-03-09","cited_by_count":65,"area":null},{"id":"2506.13206","title":"Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models","created":"2025-06-16","cited_by_count":65,"area":"lr"},{"id":"2406.13415","title":"Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators","created":"2024-06-19","cited_by_count":61,"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":"2403.12503","title":"Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices","created":"2024-03-19","cited_by_count":37,"area":null},{"id":"2507.01786","title":"Probing and Steering Evaluation Awareness of Language Models","created":"2025-07-02","cited_by_count":35,"area":null},{"id":"2312.10029","title":"Challenges with unsupervised LLM knowledge discovery","created":"2023-12-15","cited_by_count":31,"area":null},{"id":"2409.09013","title":"AI-LieDar: Examine the Trade-off Between Utility and Truthfulness in LLM Agents","created":"2024-09-13","cited_by_count":31,"area":"agents"},{"id":"2508.19461","title":"Reliable Weak-to-Strong Monitoring of LLM Agents","created":"2025-08-26","cited_by_count":31,"area":"agents"},{"id":"2502.12964","title":"Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer","created":"2025-02-18","cited_by_count":27,"area":null},{"id":"2311.15131","title":"Localizing Lying in Llama: Understanding Instructed Dishonesty on True-False Questions Through Prompting, Probing, and Patching","created":"2023-11-25","cited_by_count":24,"area":"mechinterp"},{"id":"2406.13261","title":"BeHonest: Benchmarking Honesty in Large Language Models","created":"2024-06-19","cited_by_count":24,"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":"2402.07221","title":"The Reasons that Agents Act: Intention and Instrumental Goals","created":"2024-02-11","cited_by_count":23,"area":"agents"},{"id":"2404.09971","title":"Constructing Benchmarks and Interventions for Combating Hallucinations in LLMs","created":"2024-04-15","cited_by_count":19,"area":null},{"id":"2504.07863","title":"Robust Hallucination Detection in LLMs via Adaptive Token Selection","created":"2025-04-10","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":"2403.16527","title":"Hallucination Detection in Foundation Models for Decision-Making: A Flexible Definition and Review of the State of the Art","created":"2024-03-25","cited_by_count":17,"area":null},{"id":"2405.13907","title":"Just rephrase it! Uncertainty estimation in closed-source language models via multiple rephrased queries","created":"2024-05-22","cited_by_count":15,"area":null},{"id":"2412.17128","title":"Lies, Damned Lies, and Distributional Language Statistics: Persuasion and Deception with Large Language Models","created":"2024-12-22","cited_by_count":15,"area":null},{"id":"2410.22071","title":"Distinguishing Ignorance from Error in LLM Hallucinations","created":"2024-10-29","cited_by_count":14,"area":null},{"id":"2405.05466","title":"Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals","created":"2024-05-08","cited_by_count":13,"area":null},{"id":"2410.16638","title":"LLMScan: Causal Scan for LLM Misbehavior Detection","created":"2024-10-22","cited_by_count":13,"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":"2407.09221","title":"Evaluating AI Evaluation: Perils and Prospects","created":"2024-07-12","cited_by_count":11,"area":null},{"id":"2502.19573","title":"Do Large Language Models Know How Much They Know?","created":"2025-02-26","cited_by_count":11,"area":null},{"id":"2507.22149","title":"When Truthful Representations Flip Under Deceptive Instructions?","created":"2025-07-29","cited_by_count":10,"area":"mechinterp"},{"id":"2510.14318","title":"Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RL","created":"2025-10-16","cited_by_count":10,"area":null},{"id":"2604.19117","title":"LLMs Know They're Wrong and Agree Anyway: The Shared Sycophancy-Lying Circuit","created":"2026-04-21","cited_by_count":10,"area":null},{"id":"2501.01558","title":"Predicting the Performance of Black-box LLMs through Follow-up Queries","created":"2025-01-02","cited_by_count":9,"area":null},{"id":"2505.13787","title":"Preference Learning with Lie Detectors can Induce Honesty or Evasion","created":"2025-05-20","cited_by_count":9,"area":"alignment"},{"id":"2404.05783","title":"A Survey on Responsible Generative AI: What to Generate and What Not","created":"2024-04-08","cited_by_count":8,"area":null},{"id":"2405.18718","title":"Efficient Model-agnostic Alignment via Bayesian Persuasion","created":"2024-05-29","cited_by_count":8,"area":"alignment"},{"id":"2609.29429","title":"Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures","created":"2026-09-24","cited_by_count":8,"area":"safety"},{"id":"2404.06742","title":"Transferable and Efficient Non-Factual Content Detection via Probe Training with Offline Consistency Checking","created":"2024-04-10","cited_by_count":7,"area":null},{"id":"2506.18852","title":"Mechanistic Interpretability Needs Philosophy","created":"2025-06-23","cited_by_count":6,"area":"mechinterp"},{"id":"2510.24222","title":"HACK: Hallucinations Along Certainty and Knowledge Axes","created":"2025-10-28","cited_by_count":6,"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":"2510.12826","title":"Scheming Ability in LLM-to-LLM Strategic Interactions","created":"2025-10-11","cited_by_count":5,"area":null},{"id":"2606.12618","title":"\"Did you lie?\" Evaluating Lie Detectors across Model Scale and Belief-Verified Model Organisms","created":"2026-06-10","cited_by_count":4,"area":"lr"},{"id":"2406.01931","title":"Dishonesty in Helpful and Harmless Alignment","created":"2024-06-04","cited_by_count":3,"area":"alignment"},{"id":"2409.06927","title":"Representation Tuning","created":"2024-09-11","cited_by_count":3,"area":null},{"id":"2603.02960","title":"Architecting Trust in Artificial Epistemic Agents","created":"2026-03-03","cited_by_count":3,"area":"agents"},{"id":"2509.00096","title":"Pruning Weights but Not Truth: Safeguarding Truthfulness While Pruning LLMs","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2509.21344","title":"Linear probes rely on textual evidence: Results from leakage mitigation studies in language models","created":"2025-09-16","cited_by_count":2,"area":"mechinterp"},{"id":"2510.23245","title":"Multi-Stakeholder Alignment in LLM-Powered Collaborative AI Systems: A Multi-Agent Framework for Intelligent Tutoring","created":"2025-10-27","cited_by_count":2,"area":"agents"},{"id":"2601.13709","title":"Hidden in Plain Text: Measuring LLM Deception Quality Against Human Baselines Using Social Deduction Games","created":"2026-01-20","cited_by_count":2,"area":null},{"id":"2605.27958","title":"Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations","created":"2026-05-27","cited_by_count":2,"area":"mechinterp"},{"id":"2606.17478","title":"Decoding Hidden Deception in Reasoning LLMs: Activation Explainers for Deception Auditing","created":"2026-06-16","cited_by_count":2,"area":"lr"},{"id":"2606.30449","title":"Internal-State Probes Read the Situation, Not the Action: Three Negative Results for Pre-Action Misalignment Monitoring","created":"2026-06-29","cited_by_count":2,"area":"agents"},{"id":"2608.03035","title":"Language Models Encode the Contextual Truth of Propositions","created":"2026-08-04","cited_by_count":2,"area":null},{"id":"2608.26372","title":"Knowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentives","created":"2026-08-26","cited_by_count":2,"area":"agents"},{"id":"2410.13562","title":"Enhancing Fact Retrieval in PLMs through Truthfulness","created":"2024-10-17","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":"2603.21022","title":"Knowledge Boundary Discovery for Large Language Models","created":"2026-01-14","cited_by_count":1,"area":null},{"id":"2607.14111","title":"Introspection Fine-Tuning (IFT): Training Small LLMs to Introspect","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2508.00881","title":"Hallucination Detection and Mitigation with Diffusion in Multi-Variate Time-Series Foundation Models","created":"2025-07-23","cited_by_count":0,"area":null},{"id":"2510.01288","title":"Microsaccade-Inspired Probing: Positional Encoding Perturbations Reveal LLM Misbehaviours","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2511.01956","title":"Vibe Learning: Education in the age of AI","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":"2603.14672","title":"Seamless Deception: Larger Language Models Are Better Knowledge Concealers","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2605.09391","title":"Do Linear Probes Generalize Better in Persona Coordinates?","created":"2026-05-10","cited_by_count":0,"area":"mechinterp"},{"id":"2605.18801","title":"Position: Let's Develop Data Probes to Fundamentally Understand How Data Affects LLM Performance","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.19270","title":"DECOR: Auditing LLM Deception via Information Manipulation Theory","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.10747","title":"The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment","created":"2026-06-09","cited_by_count":0,"area":"agents"},{"id":"2607.20479","title":"Beyond Liars' Bench: The Impact of Lie Typology, Depth, and Sparsity on Deception Detection in LLMs","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2609.21996","title":"A Lie Detector Test for Language Models: Reading Knowledge a Model Won't Reveal","created":"2026-09-18","cited_by_count":0,"area":"safety"},{"id":"2609.22043","title":"An Interpretable Memory Decision Controller for LLM Agents Based on Three-Signal Complementarity: Decoupling Confidence and Consistency","created":"2026-09-18","cited_by_count":0,"area":"agents"},{"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},{"id":"2610.20179","title":"Cross-Model In-Context Neurofeedback Reveals (Limited) Activation Control in LLMs","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}