{"total":79,"rows":[{"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":"2503.01822","title":"Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry","created":"2025-03-03","cited_by_count":61,"area":"mechinterp"},{"id":"2502.01563","title":"Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding","created":"2025-02-03","cited_by_count":47,"area":null},{"id":"2509.10625","title":"No Answer Needed: Predicting LLM Answer Accuracy from Question-Only Linear Probes","created":"2025-09-12","cited_by_count":38,"area":"mechinterp"},{"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":"2603.17839","title":"How do LLMs Compute Verbal Confidence","created":"2026-03-18","cited_by_count":26,"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":"2511.06626","title":"Spilling the Beans: Teaching LLMs to Self-Report Their Hidden Objectives","created":"2025-11-10","cited_by_count":15,"area":"agents"},{"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":"2504.02904","title":"How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence","created":"2025-04-03","cited_by_count":12,"area":null},{"id":"2505.18658","title":"Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics","created":"2025-05-24","cited_by_count":12,"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":"2602.15515","title":"The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes","created":"2026-02-17","cited_by_count":12,"area":null},{"id":"2510.05184","title":"Representation Potentials of Foundation Models for Multimodal Alignment: A Survey","created":"2025-10-05","cited_by_count":11,"area":null},{"id":"2506.05451","title":"Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety","created":"2025-06-05","cited_by_count":10,"area":"safety"},{"id":"2506.15538","title":"Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework","created":"2025-06-18","cited_by_count":10,"area":null},{"id":"2507.22149","title":"When Truthful Representations Flip Under Deceptive Instructions?","created":"2025-07-29","cited_by_count":10,"area":"mechinterp"},{"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":"2412.12276","title":"Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective","created":"2024-12-16","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":"2508.19432","title":"Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs","created":"2025-08-26","cited_by_count":9,"area":null},{"id":"2411.04847","title":"Prompt-Guided Internal States for Hallucination Detection of Large Language Models","created":"2024-11-07","cited_by_count":8,"area":null},{"id":"2602.20273","title":"The Truthfulness Spectrum Hypothesis","created":"2026-02-23","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":"2509.03518","title":"Can LLMs Lie? Investigation beyond Hallucination","created":"2025-09-03","cited_by_count":7,"area":"mechinterp"},{"id":"2606.07612","title":"Position: Anthropomorphic Misalignment Research Needs Stronger Evidence","created":"2026-05-29","cited_by_count":7,"area":null},{"id":"2504.13816","title":"Analyzing LLMs' Knowledge Boundary Cognition Across Languages Through the Lens of Internal Representations","created":"2025-04-18","cited_by_count":6,"area":null},{"id":"2510.24222","title":"HACK: Hallucinations Along Certainty and Knowledge Axes","created":"2025-10-28","cited_by_count":6,"area":null},{"id":"2501.19398","title":"Do LLMs Strategically Reveal, Conceal, and Infer Information? A Theoretical and Empirical Analysis in The Chameleon Game","created":"2025-01-31","cited_by_count":5,"area":"agents"},{"id":"2507.07544","title":"Position: We Need An Algorithmic Understanding of Generative AI","created":"2025-07-10","cited_by_count":5,"area":null},{"id":"2509.11536","title":"HARP: Hallucination Detection via Reasoning Subspace Projection","created":"2025-09-15","cited_by_count":5,"area":"lr"},{"id":"2505.21800","title":"From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2509.13154","title":"LLM Hallucination Detection: A Fast Fourier Transform Method Based on Hidden Layer Temporal Signals","created":"2025-09-16","cited_by_count":4,"area":null},{"id":"2601.14210","title":"DRIFT: Detecting Representational Inconsistencies for Factual Truthfulness","created":"2026-01-20","cited_by_count":4,"area":null},{"id":"2602.08159","title":"The Confidence Manifold: Geometric Structure of Correctness Representations in Language Models","created":"2026-02-08","cited_by_count":4,"area":"mechinterp"},{"id":"2604.04496","title":"The Indra Representation Hypothesis for Multimodal Alignment","created":"2026-04-06","cited_by_count":4,"area":null},{"id":"2604.13386","title":"Linear Probe Accuracy Scales with Model Size and Benefits from Multi-Layer Ensembling","created":"2026-04-15","cited_by_count":4,"area":"alignment"},{"id":"2501.18887","title":"Towards Unified Attribution in Explainable AI, Data-Centric AI, and Mechanistic Interpretability","created":"2025-01-31","cited_by_count":3,"area":"mechinterp"},{"id":"2505.08662","title":"Revealing economic facts: LLMs know more than they say","created":"2025-05-13","cited_by_count":3,"area":null},{"id":"2511.07318","title":"When Bias Pretends to Be Truth: How Spurious Correlations Undermine Hallucination Detection in LLMs","created":"2025-11-10","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":"2601.23211","title":"Multi-Agent Systems Should be Treated as Principal-Agent Problems","created":"2026-01-30","cited_by_count":3,"area":"agents"},{"id":"2604.22271","title":"How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals","created":"2026-04-24","cited_by_count":3,"area":null},{"id":"2505.12182","title":"Truth Neurons","created":"2025-05-18","cited_by_count":2,"area":null},{"id":"2506.16150","title":"PRISON: Unmasking the Criminal Potential of Large Language Models","created":"2025-06-19","cited_by_count":2,"area":null},{"id":"2507.09406","title":"Adversarial Activation Patching: A Framework for Detecting and Mitigating Emergent Deception in Safety-Aligned Transformers","created":"2025-07-12","cited_by_count":2,"area":"alignment"},{"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":"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":"2604.03754","title":"Testing the Limits of Truth Directions in LLMs","created":"2026-04-04","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":"2608.03035","title":"Language Models Encode the Contextual Truth of Propositions","created":"2026-08-04","cited_by_count":2,"area":null},{"id":"2609.18080","title":"Decodability is Not Causality: Dissociating Probe Readouts from Behavioral Drivers via SAE Decomposition","created":"2026-09-16","cited_by_count":2,"area":"mechinterp"},{"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":"2509.23580","title":"LLM Hallucination Detection: HSAD","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2511.19166","title":"Epistemic Familiarity is Associated With Belief Stability in Large Language Models","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2511.21737","title":"Polarity-Aware Probing for Quantifying Latent Alignment in Language Models","created":"2025-11-21","cited_by_count":1,"area":"alignment"},{"id":"2601.06599","title":"How Context Shapes Truth: Geometric Transformations of Statement-level Truth Representations in LLMs","created":"2026-01-10","cited_by_count":1,"area":null},{"id":"2603.11749","title":"Truth as a Compression Artifact in Language Model Training","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2604.11662","title":"A Robust Evaluation of Probe Robustness: Lessons for Reliable OOD Uncertainty Quantification","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2607.27824","title":"STEREODISCO: Discovering Stereotypicality in LLMs","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2608.28930","title":"The Hallucination Signal Is a Mean Shift: Why Simple Probes Suffice","created":"2026-08-28","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":"2602.14529","title":"Disentangling Deception and Hallucination Failures in LLMs","created":"2026-02-16","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":"2604.24801","title":"Architecture Determines Observability of Transformers","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.30675","title":"Human-Alignment, Calibration, and Activation Patterns in Large Language Model Uncertainty","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.01006","title":"Understanding Large Language Models","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.14791","title":"Transcoders for Investigating Deception in Language Models","created":"2026-07-16","cited_by_count":0,"area":"mechinterp"},{"id":"2607.16741","title":"The Anatomy of a Truth Direction: Knowledge-Dependent Dimensionality, a Relational Law, and a Shared Category Geometry in Small Language Models","created":"2026-07-18","cited_by_count":0,"area":null},{"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":"2608.26222","title":"NeuronFuzz: Safety Neuron Guided Fuzzing for LLM Safety Evaluation","created":"2026-08-26","cited_by_count":0,"area":"alignment"},{"id":"2609.00519","title":"The Safeguard Worked. Is the LLM System Safer?","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.01361","title":"Investigating Linear Probe Robustness to Linguistic Register, Medical Specialty, and Corpus Shifts in Medical QA","created":"2026-09-01","cited_by_count":0,"area":"mechinterp"},{"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":"2609.34678","title":"Fair Fact-Checking: Closing the Cross-Lingual Gap in LLM Factual Judgement with RoSh","created":"2026-09-28","cited_by_count":0,"area":null},{"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":"2610.08018","title":"Structured but Silent: Probing Capability Requirements in LLM Hidden States","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}