{"total":441,"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":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302,"area":null},{"id":"2307.05782","title":"Large Language Models","created":"2023-07-11","cited_by_count":780,"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":"2304.13734","title":"The Internal State of an LLM Knows When It's Lying","created":"2023-04-26","cited_by_count":659,"area":null},{"id":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334,"area":null},{"id":"2310.02207","title":"Language Models Represent Space and Time","created":"2023-10-03","cited_by_count":316,"area":null},{"id":"2502.02013","title":"Layer by Layer: Uncovering Hidden Representations in Language Models","created":"2025-02-04","cited_by_count":311,"area":null},{"id":"2406.15927","title":"Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs","created":"2024-06-22","cited_by_count":259,"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":"2311.06668","title":"In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering","created":"2023-11-11","cited_by_count":245,"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":"2405.05904","title":"Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?","created":"2024-05-09","cited_by_count":232,"area":null},{"id":"2306.12001","title":"An Overview of Catastrophic AI Risks","created":"2023-06-21","cited_by_count":222,"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":"2305.15324","title":"Model evaluation for extreme risks","created":"2023-05-24","cited_by_count":177,"area":null},{"id":"2406.01506","title":"The Geometry of Categorical and Hierarchical Concepts in Large Language Models","created":"2024-06-03","cited_by_count":159,"area":null},{"id":"2310.13018","title":"Getting aligned on representational alignment","created":"2023-10-18","cited_by_count":143,"area":null},{"id":"2407.07071","title":"Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps","created":"2024-07-09","cited_by_count":142,"area":null},{"id":"2304.00740","title":"Inspecting and Editing Knowledge Representations in Language Models","created":"2023-04-03","cited_by_count":141,"area":null},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"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":"2406.02543","title":"To Believe or Not to Believe Your LLM","created":"2024-06-04","cited_by_count":120,"area":null},{"id":"2302.06600","title":"Task-Specific Skill Localization in Fine-tuned Language Models","created":"2023-02-13","cited_by_count":105,"area":null},{"id":"2307.16513","title":"Deception Abilities Emerged in Large Language Models","created":"2023-07-31","cited_by_count":101,"area":null},{"id":"2406.08391","title":"Large Language Models Must Be Taught to Know What They Don't Know","created":"2024-06-12","cited_by_count":100,"area":null},{"id":"2409.17504","title":"HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection","created":"2024-09-26","cited_by_count":99,"area":null},{"id":"2305.16130","title":"Language Models Implement Simple Word2Vec-style Vector Arithmetic","created":"2023-05-25","cited_by_count":98,"area":null},{"id":"2402.17811","title":"TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space","created":"2024-02-27","cited_by_count":91,"area":null},{"id":"2405.16908","title":"Can Large Language Models Faithfully Express Their Intrinsic Uncertainty in Words?","created":"2024-05-27","cited_by_count":87,"area":null},{"id":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"area":null},{"id":"2309.15840","title":"How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions","created":"2023-09-26","cited_by_count":83,"area":null},{"id":"2310.06271","title":"Towards Mitigating Hallucination in Large Language Models via Self-Reflection","created":"2023-10-10","cited_by_count":81,"area":null},{"id":"2403.03867","title":"On the Origins of Linear Representations in Large Language Models","created":"2024-03-06","cited_by_count":79,"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":"2307.00175","title":"Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblocks","created":"2023-06-30","cited_by_count":78,"area":null},{"id":"2404.15993","title":"Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approach","created":"2024-04-24","cited_by_count":76,"area":null},{"id":"2304.00612","title":"Eight Things to Know about Large Language Models","created":"2023-04-02","cited_by_count":73,"area":null},{"id":"2506.11618","title":"Convergent Linear Representations of Emergent Misalignment","created":"2025-06-13","cited_by_count":71,"area":null},{"id":"2403.17752","title":"Can multiple-choice questions really be useful in detecting the abilities of LLMs?","created":"2024-03-26","cited_by_count":69,"area":null},{"id":"2309.15098","title":"Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models","created":"2023-09-26","cited_by_count":67,"area":null},{"id":"2409.20089","title":"Robust LLM safeguarding via refusal feature adversarial training","created":"2024-09-30","cited_by_count":64,"area":null},{"id":"2312.01037","title":"Eliciting Latent Knowledge from Quirky Language Models","created":"2023-12-02","cited_by_count":62,"area":null},{"id":"2312.03729","title":"Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness?","created":"2023-11-27","cited_by_count":62,"area":null},{"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":"2406.16254","title":"Confidence Regulation Neurons in Language Models","created":"2024-06-24","cited_by_count":57,"area":null},{"id":"2410.13640","title":"Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation","created":"2024-10-17","cited_by_count":57,"area":null},{"id":"2506.10805","title":"Detecting High-Stakes Interactions with Activation Probes","created":"2025-06-12","cited_by_count":53,"area":null},{"id":"2401.13275","title":"Can AI Assistants Know What They Don't Know?","created":"2024-01-24","cited_by_count":50,"area":null},{"id":"2501.00070","title":"ICLR: In-Context Learning of Representations","created":"2024-12-29","cited_by_count":50,"area":null},{"id":"2503.01917","title":"Steer LLM Latents for Hallucination Detection","created":"2025-03-01","cited_by_count":50,"area":null},{"id":"2410.05864","title":"From Tokens to Words: On the Inner Lexicon of LLMs","created":"2024-10-08","cited_by_count":48,"area":null},{"id":"2503.14477","title":"Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations","created":"2025-03-18","cited_by_count":48,"area":null},{"id":"2306.09983","title":"Evaluating Superhuman Models with Consistency Checks","created":"2023-06-16","cited_by_count":47,"area":null},{"id":"2308.01404","title":"Hoodwinked: Deception and Cooperation in a Text-Based Game for Language Models","created":"2023-07-05","cited_by_count":47,"area":null},{"id":"2310.18168","title":"Personas as a Way to Model Truthfulness in Language Models","created":"2023-10-27","cited_by_count":47,"area":null},{"id":"2402.03563","title":"Distinguishing the Knowable from the Unknowable with Language Models","created":"2024-02-05","cited_by_count":47,"area":null},{"id":"2403.08946","title":"Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era","created":"2024-03-13","cited_by_count":46,"area":null},{"id":"2312.17484","title":"Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuning","created":"2023-12-29","cited_by_count":45,"area":null},{"id":"2402.18048","title":"Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension","created":"2024-02-28","cited_by_count":45,"area":null},{"id":"2310.01846","title":"Benchmarking and Improving Generator-Validator Consistency of Language Models","created":"2023-10-03","cited_by_count":44,"area":null},{"id":"2401.15449","title":"Learning to Trust Your Feelings: Leveraging Self-awareness in LLMs for Hallucination Mitigation","created":"2024-01-27","cited_by_count":44,"area":null},{"id":"2402.14433","title":"A Language Model's Guide Through Latent Space","created":"2024-02-22","cited_by_count":43,"area":null},{"id":"2306.02109","title":"Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency","created":"2023-06-03","cited_by_count":42,"area":null},{"id":"2412.12472","title":"Knowledge Boundary of Large Language Models: A Survey","created":"2024-12-17","cited_by_count":40,"area":null},{"id":"2410.14273","title":"REEF: Representation Encoding Fingerprints for Large Language Models","created":"2024-10-18","cited_by_count":36,"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":"2307.03637","title":"Discovering Variable Binding Circuitry with Desiderata","created":"2023-07-07","cited_by_count":34,"area":null},{"id":"2410.10014","title":"Safety-Aware Fine-Tuning of Large Language Models","created":"2024-10-13","cited_by_count":34,"area":null},{"id":"2412.09563","title":"Does Representation Matter? Exploring Intermediate Layers in Large Language Models","created":"2024-12-12","cited_by_count":34,"area":null},{"id":"2406.14785","title":"Understanding Finetuning for Factual Knowledge Extraction","created":"2024-06-20","cited_by_count":32,"area":null},{"id":"2303.10475","title":"Large Language Model Instruction Following: A Survey of Progresses and Challenges","created":"2023-03-18","cited_by_count":31,"area":null},{"id":"2310.06827","title":"Teaching Language Models to Hallucinate Less with Synthetic Tasks","created":"2023-10-10","cited_by_count":31,"area":null},{"id":"2312.10029","title":"Challenges with unsupervised LLM knowledge discovery","created":"2023-12-15","cited_by_count":31,"area":null},{"id":"2402.18496","title":"Language Models Represent Beliefs of Self and Others","created":"2024-02-28","cited_by_count":31,"area":null},{"id":"2309.07418","title":"A Fast Optimization View: Reformulating Single Layer Attention in LLM Based on Tensor and SVM Trick, and Solving It in Matrix Multiplication Time","created":"2023-09-14","cited_by_count":30,"area":null},{"id":"2405.21030","title":"Standards for Belief Representations in LLMs","created":"2024-05-31","cited_by_count":30,"area":null},{"id":"2406.12053","title":"InternalInspector $I^2$: Robust Confidence Estimation in LLMs through Internal States","created":"2024-06-17","cited_by_count":30,"area":null},{"id":"2410.22685","title":"Improving Uncertainty Quantification in Large Language Models via Semantic Embeddings","created":"2024-10-30","cited_by_count":30,"area":null},{"id":"2402.09236","title":"Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Models","created":"2024-02-14","cited_by_count":29,"area":null},{"id":"2404.03189","title":"The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models","created":"2024-04-04","cited_by_count":29,"area":null},{"id":"2410.00153","title":"Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution","created":"2024-09-30","cited_by_count":27,"area":null},{"id":"2412.18544","title":"Consistency Checks for Language Model Forecasters","created":"2024-12-24","cited_by_count":27,"area":null},{"id":"2410.14516","title":"Do LLMs \"know\" internally when they follow instructions?","created":"2024-10-18","cited_by_count":26,"area":null},{"id":"2603.17839","title":"How do LLMs Compute Verbal Confidence","created":"2026-03-18","cited_by_count":26,"area":null},{"id":"2409.09951","title":"Optimal ablation for interpretability","created":"2024-09-16","cited_by_count":25,"area":null},{"id":"2502.07586","title":"We Can't Understand AI Using our Existing Vocabulary","created":"2025-02-11","cited_by_count":25,"area":null},{"id":"2406.13261","title":"BeHonest: Benchmarking Honesty in Large Language Models","created":"2024-06-19","cited_by_count":24,"area":null},{"id":"2407.08582","title":"On the Universal Truthfulness Hyperplane Inside LLMs","created":"2024-07-11","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":"2308.10502","title":"GradientCoin: A Peer-to-Peer Decentralized Large Language Models","created":"2023-08-21","cited_by_count":23,"area":null},{"id":"2404.06921","title":"GoEX: Perspectives and Designs Towards a Runtime for Autonomous LLM Applications","created":"2024-04-10","cited_by_count":23,"area":null},{"id":"2310.08043","title":"Understanding and Controlling a Maze-Solving Policy Network","created":"2023-10-12","cited_by_count":22,"area":null},{"id":"2311.08576","title":"Towards Evaluating AI Systems for Moral Status Using Self-Reports","created":"2023-11-14","cited_by_count":22,"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":"2505.16270","title":"Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning","created":"2025-05-22","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":"2406.07457","title":"Estimating the Hallucination Rate of Generative AI","created":"2024-06-11","cited_by_count":20,"area":null},{"id":"2409.12915","title":"Exploring Representations and Interventions in Time Series Foundation Models","created":"2024-09-19","cited_by_count":20,"area":null},{"id":"2502.11812","title":"Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis","created":"2025-02-17","cited_by_count":20,"area":null}],"next_cursor":"100"}