{"total":22,"rows":[{"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":"2403.19851","title":"Localizing Paragraph Memorization in Language Models","created":"2024-03-28","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":"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":"2510.13290","title":"To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models","created":"2025-10-15","cited_by_count":29,"area":null},{"id":"2406.19354","title":"Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs?","created":"2024-06-27","cited_by_count":24,"area":null},{"id":"2404.14068","title":"Holistic Safety and Responsibility Evaluations of Advanced AI Models","created":"2024-04-22","cited_by_count":19,"area":null},{"id":"2506.10139","title":"Unsupervised Elicitation of Language Models","created":"2025-06-11","cited_by_count":11,"area":null},{"id":"2401.16713","title":"Prospects for inconsistency detection using large language models and sheaves","created":"2024-01-30","cited_by_count":10,"area":null},{"id":"2503.17755","title":"Improving Preference Extraction In LLMs By Identifying Latent Knowledge Through Classifying Probes","created":"2025-03-22","cited_by_count":9,"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":"2410.02499","title":"Defining Knowledge: Bridging Epistemology and Large Language Models","created":"2024-10-03","cited_by_count":7,"area":null},{"id":"2412.15265","title":"Chinese SafetyQA: A Safety Short-form Factuality Benchmark for Large Language Models","created":"2024-12-17","cited_by_count":7,"area":null},{"id":"2405.00301","title":"Enhanced Language Model Truthfulness with Learnable Intervention and Uncertainty Expression","created":"2024-05-01","cited_by_count":6,"area":null},{"id":"2407.18712","title":"Cluster-norm for Unsupervised Probing of Knowledge","created":"2024-07-26","cited_by_count":4,"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":"2508.06030","title":"Efficient Knowledge Probing of Large Language Models by Adapting Pre-trained Embeddings","created":"2025-08-08","cited_by_count":3,"area":null},{"id":"2606.17229","title":"Rift: A Conflict Signature for Deception in Language Models","created":"2026-06-15","cited_by_count":1,"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":"2601.17728","title":"Unsupervised Elicitation of Moral Values from Language Models","created":"2026-01-25","cited_by_count":0,"area":null},{"id":"2609.31401","title":"Decodable In-Context State and Model Output Across Training","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2610.04174","title":"DimSteer: Steering LLM Authoring with Automatically Discovered Stylistic Controls","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}