{"total":52,"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":"2509.03531","title":"Real-Time Detection of Hallucinated Entities in Long-Form Generation","created":"2025-08-26","cited_by_count":34,"area":null},{"id":"2504.03022","title":"The Dual-Route Model of Induction","created":"2025-04-03","cited_by_count":24,"area":null},{"id":"2505.20322","title":"Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms","created":"2025-05-23","cited_by_count":24,"area":null},{"id":"2502.12414","title":"Lost in Transcription, Found in Distribution Shift: Demystifying Hallucination in Speech Foundation Models","created":"2025-02-18","cited_by_count":18,"area":null},{"id":"2507.20957","title":"Your AI, Not Your View: The Bias of LLMs in Investment Analysis","created":"2025-07-28","cited_by_count":17,"area":null},{"id":"2509.25175","title":"EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering","created":"2025-09-29","cited_by_count":13,"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":"2602.15669","title":"PERSONA: Dynamic and Compositional Inference-Time Personality Control via Activation Vector Algebra","created":"2026-02-17","cited_by_count":12,"area":null},{"id":"2505.11770","title":"Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors","created":"2025-05-17","cited_by_count":11,"area":null},{"id":"2506.10139","title":"Unsupervised Elicitation of Language Models","created":"2025-06-11","cited_by_count":11,"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":"2507.08017","title":"Mechanistic Indicators of Understanding in Large Language Models","created":"2025-07-07","cited_by_count":8,"area":null},{"id":"2502.14445","title":"PredictaBoard: Benchmarking LLM Score Predictability","created":"2025-02-20","cited_by_count":7,"area":null},{"id":"2509.14223","title":"Fresh in memory: Training-order recency is linearly encoded in language model activations","created":"2025-09-17","cited_by_count":6,"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":"2509.09700","title":"Cross-Layer Attention Probing for Fine-Grained Hallucination Detection","created":"2025-09-04","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":"2601.16766","title":"Do LLM hallucination detectors suffer from low-resource effect?","created":"2026-01-23","cited_by_count":4,"area":null},{"id":"2604.01457","title":"Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs","created":"2026-04-01","cited_by_count":4,"area":null},{"id":"2511.07001","title":"SCOPE: Intrinsic Semantic Space Control for Mitigating Copyright Infringement in LLMs","created":"2025-11-10","cited_by_count":3,"area":null},{"id":"2512.24560","title":"Localized Calibrated Uncertainty in Code Language Models","created":"2025-12-31","cited_by_count":3,"area":null},{"id":"2601.15334","title":"No Reliable Evidence of Self-Reported Sentience in Small Large Language Models","created":"2026-01-20","cited_by_count":3,"area":null},{"id":"2603.05881","title":"Confidence Before Answering: A Paradigm Shift for Efficient LLM Uncertainty Estimation","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2604.12373","title":"Masked by Consensus: Disentangling Privileged Knowledge in LLM Correctness","created":"2026-04-14","cited_by_count":3,"area":null},{"id":"2605.17028","title":"PARALLAX: Separating Genuine Hallucination Detection from Benchmark Construction Artifacts","created":"2026-05-16","cited_by_count":3,"area":null},{"id":"2504.02865","title":"The Illusionist's Prompt: Exposing the Factual Vulnerabilities of Large Language Models with Linguistic Nuances","created":"2025-04-01","cited_by_count":2,"area":null},{"id":"2505.12182","title":"Truth Neurons","created":"2025-05-18","cited_by_count":2,"area":null},{"id":"2505.21399","title":"Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2510.20690","title":"Neural Diversity Regularizes Hallucinations in Language Models","created":"2025-10-23","cited_by_count":2,"area":null},{"id":"2510.26935","title":"RepV: Safety-Separable Latent Spaces for Scalable Neurosymbolic Plan Verification","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2602.02018","title":"Do I Really Know? Learning Factual Self-Verification for Hallucination Reduction","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2603.10771","title":"Word Recovery in Large Language Models Enables Character-Level Tokenization Robustness","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2606.11105","title":"PhantomBench: Benchmarking the Non-existential Threat of Language Models","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2507.06722","title":"On the Effect of Uncertainty on Layer-wise Inference Dynamics","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2510.04048","title":"Increasing LLM response trustworthiness using voting ensembles","created":"2025-10-05","cited_by_count":1,"area":null},{"id":"2510.09421","title":"On the Representations of Entities in Auto-regressive Large Language Models","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2601.11429","title":"Relational Linearity is a Predictor of Hallucinations","created":"2026-01-16","cited_by_count":1,"area":null},{"id":"2603.18446","title":"UT-ACA: Uncertainty-Triggered Adaptive Context Allocation for Long-Context Inference","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2607.07670","title":"Does Bielik Know What It Doesn't Know? Activation Dispersion Separates Entity Familiarity from Factual Reliability Across Model Scale","created":"2026-07-08","cited_by_count":1,"area":null},{"id":"2608.18115","title":"Temporal Multi-Signal Fusion for Token-Level Hallucination Detection","created":"2026-06-30","cited_by_count":1,"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":"2602.09486","title":"Listen to the Layers: Mitigating Hallucinations with Inter-Layer Disagreement","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2602.14529","title":"Disentangling Deception and Hallucination Failures in LLMs","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2602.22453","title":"Identifying Crucial Attention Heads for Multilingual Language Models: Retrieval and Retrieval-Transition Heads","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2605.05025","title":"Detecting Hallucinations in Large Language Models via Internal Attention Divergence Signals","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2606.21595","title":"Per-Entity Bias Mapping for AI Visibility: Why Brand Mentions Require Entity-Specific Calibration","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2607.13568","title":"Graded Entity-Familiarity Readouts in Language Models: Polish Adaptation, Cross-Language Robustness, and Refusal Steering","created":"2026-07-15","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},{"id":"2609.33142","title":"Knowing Is Not Choosing: What Explicit Verification Adds Beyond Generative Preference","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.35663","title":"Late Attention Layers Alone Can Copy Entity Tokens, but Not Without Attending to Their Context","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}