{"total":30,"rows":[{"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":"2406.11267","title":"Mitigating Large Language Model Hallucination with Faithful Finetuning","created":"2024-06-17","cited_by_count":24,"area":null},{"id":"2412.11965","title":"Inferring Functionality of Attention Heads from their Parameters","created":"2024-12-16","cited_by_count":17,"area":null},{"id":"2407.03779","title":"Sheaf Discovery with Joint Computation Graph Pruning and Flexible Granularity","created":"2024-07-04","cited_by_count":14,"area":null},{"id":"2510.15804","title":"Emergence of Linear Truth Encodings in Language Models","created":"2025-10-17","cited_by_count":12,"area":null},{"id":"2507.23221","title":"A Single Direction of Truth: An Observer Model's Linear Residual Probe Exposes and Steers Contextual Hallucinations","created":"2025-07-31","cited_by_count":9,"area":null},{"id":"2509.21972","title":"From Superficial Outputs to Superficial Learning: Risks of Large Language Models in Education","created":"2025-09-26","cited_by_count":9,"area":null},{"id":"2506.06382","title":"On the Fundamental Impossibility of Hallucination Control in Large Language Models","created":"2025-06-04","cited_by_count":7,"area":null},{"id":"2503.23361","title":"Discovering Knowledge Deficiencies of Language Models on Massive Knowledge Base","created":"2025-03-30","cited_by_count":6,"area":null},{"id":"2505.09338","title":"Llama See, Llama Do: A Mechanistic Perspective on Contextual Entrainment and Distraction in LLMs","created":"2025-05-14","cited_by_count":6,"area":null},{"id":"2505.22630","title":"Stochastic Chameleons: Irrelevant Context Hallucinations Reveal Class-Based (Mis)Generalization in LLMs","created":"2025-05-28","cited_by_count":6,"area":null},{"id":"2505.06032","title":"Short-circuiting Shortcuts: Mechanistic Investigation of Shortcuts in Text Classification","created":"2025-05-09","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":"2505.15386","title":"RePPL: Recalibrating Perplexity by Uncertainty in Semantic Propagation and Language Generation for Explainable QA Hallucination Detection","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2509.06938","title":"From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers","created":"2025-09-08","cited_by_count":4,"area":null},{"id":"2510.06107","title":"Distributional Semantics Tracing: A Framework for Explaining Hallucinations in Large Language Models","created":"2025-10-07","cited_by_count":3,"area":null},{"id":"2510.20690","title":"Neural Diversity Regularizes Hallucinations in Language Models","created":"2025-10-23","cited_by_count":2,"area":null},{"id":"2605.07209","title":"Hallucination Detection via Activations of Open-Weight Proxy Analyzers","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2505.21218","title":"Pretrained LLMs Learn Multiple Types of Uncertainty","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2511.14172","title":"SymLoc: Symbolic Localization of Hallucination across HaluEval and TruthfulQA","created":"2025-11-18","cited_by_count":1,"area":null},{"id":"2605.22864","title":"Reading Calibrated Uncertainty from Language Model Trajectories","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2606.03022","title":"Hallucinations as Orthogonal Noise: Inference-Time Manifold Alignment via Dynamic Contextual Orthogonalization","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2505.20451","title":"Amulet: Putting Complex Multi-Turn Conversations on the Stand with LLM Juries","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2512.00931","title":"Mitigating Hallucinations in Zero-Shot Scientific Summarisation: A Pilot Study","created":"2025-11-30","cited_by_count":0,"area":null},{"id":"2602.09486","title":"Listen to the Layers: Mitigating Hallucinations with Inter-Layer Disagreement","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2602.13264","title":"Directional Concentration Uncertainty: A representational approach to uncertainty quantification for generative models","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2605.18163","title":"TRACE: Trajectory Correction from Cross-layer Evidence for Hallucination Reduction","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.30481","title":"When English Rewrites Local Knowledge: Global Narrative Dominance in Large Language Models","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2607.18292","title":"Reliability Scales Inversely: Hallucinations Snowball Faster in Bigger Language Models","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2609.14448","title":"NeuroActiSep: Detecting Factual Hallucinations from Feed-Forward Neurons in a Single Pass","created":"2026-09-13","cited_by_count":0,"area":null}],"next_cursor":null}