{"total":82,"rows":[{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2409.03752","title":"Attention Heads of Large Language Models: A Survey","created":"2024-09-05","cited_by_count":67,"area":null},{"id":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51,"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":"2412.12472","title":"Knowledge Boundary of Large Language Models: A Survey","created":"2024-12-17","cited_by_count":40,"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":"2509.03531","title":"Real-Time Detection of Hallucinated Entities in Long-Form Generation","created":"2025-08-26","cited_by_count":34,"area":null},{"id":"2502.01042","title":"SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals","created":"2025-02-03","cited_by_count":29,"area":"safety"},{"id":"2409.18786","title":"A Survey on the Honesty of Large Language Models","created":"2024-09-27","cited_by_count":23,"area":"alignment"},{"id":"2502.21239","title":"Semantic Volume: Quantifying and Detecting both External and Internal Uncertainty in LLMs","created":"2025-02-28","cited_by_count":20,"area":null},{"id":"2502.06258","title":"Emergent Response Planning in LLMs","created":"2025-02-10","cited_by_count":19,"area":"lr"},{"id":"2504.07863","title":"Robust Hallucination Detection in LLMs via Adaptive Token Selection","created":"2025-04-10","cited_by_count":19,"area":null},{"id":"2501.19358","title":"The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking","created":"2025-01-31","cited_by_count":18,"area":"alignment"},{"id":"2501.12934","title":"Correctness Assessment of Code Generated by Large Language Models Using Internal Representations","created":"2025-01-22","cited_by_count":17,"area":null},{"id":"2507.16372","title":"Depth Gives a False Sense of Privacy: LLM Internal States Inversion","created":"2025-07-22","cited_by_count":17,"area":null},{"id":"2410.22071","title":"Distinguishing Ignorance from Error in LLM Hallucinations","created":"2024-10-29","cited_by_count":14,"area":null},{"id":"2412.11803","title":"UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models","created":"2024-12-16","cited_by_count":13,"area":"alignment"},{"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":"2506.05451","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":"2510.09033","title":"Do LLMs Really Know What They Don't Know? Internal States Mainly Reflect Knowledge Recall Rather Than Truthfulness","created":"2025-10-10","cited_by_count":10,"area":null},{"id":"2505.13529","title":"BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs","created":"2025-05-18","cited_by_count":8,"area":"lr"},{"id":"2507.02870","title":"Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models","created":"2025-06-06","cited_by_count":7,"area":null},{"id":"2608.02657","title":"Your Agentic LLMs Secretly Encode Indirect Prompt-Injection Exposure in Hidden States","created":"2026-08-01","cited_by_count":7,"area":"agents"},{"id":"2504.00446","title":"Exposing the Ghost in the Transformer: Abnormal Detection for Large Language Models via Hidden State Forensics","created":"2025-04-01","cited_by_count":6,"area":"safety"},{"id":"2504.04335","title":"Hallucinated Span Detection with Multi-View Attention Features","created":"2025-04-06","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":"2601.05866","title":"FACTUM: Mechanistic Detection of Citation Hallucination in Long-Form RAG","created":"2026-01-09","cited_by_count":6,"area":"rag"},{"id":"2604.05306","title":"LLMs Should Express Uncertainty Explicitly","created":"2026-04-07","cited_by_count":6,"area":null},{"id":"2506.21590","title":"Representation Consistency for Accurate and Coherent LLM Answer Aggregation","created":"2025-06-18","cited_by_count":5,"area":"lr"},{"id":"2510.02173","title":"Learning to Reason for Hallucination Span Detection","created":"2025-10-02","cited_by_count":5,"area":"lr"},{"id":"2602.13699","title":"Gradient-Stable Attention Heads Signal LLM Correctness","created":"2026-02-14","cited_by_count":5,"area":null},{"id":"2502.01025","title":"Knowing When to Stop: Efficient Context Processing via Latent Sufficiency Signals","created":"2025-02-03","cited_by_count":4,"area":"inference"},{"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":"2506.12450","title":"Language Surgery in Multilingual Large Language Models","created":"2025-06-14","cited_by_count":4,"area":null},{"id":"2607.06503","title":"Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade","created":"2026-07-07","cited_by_count":4,"area":"agents"},{"id":"2409.16913","title":"Tell Me What You Don't Know: Enhancing Refusal Capabilities of Role-Playing Agents via Representation Space Analysis and Editing","created":"2024-09-25","cited_by_count":3,"area":null},{"id":"2505.19073","title":"Towards Harmonized Uncertainty Estimation for Large Language Models","created":"2025-05-25","cited_by_count":3,"area":null},{"id":"2506.06240","title":"Bridging External and Parametric Knowledge: Mitigating Hallucination of LLMs with Shared-Private Semantic Synergy in Dual-Stream Knowledge","created":"2025-06-06","cited_by_count":3,"area":"rag"},{"id":"2507.14649","title":"Cleanse: Uncertainty Estimation Approach Using Clustering-based Semantic Consistency in LLMs","created":"2025-07-19","cited_by_count":3,"area":null},{"id":"2509.00072","title":"Test of Time: Rethinking Temporal Signal of Benchmark Contamination","created":"2025-08-26","cited_by_count":3,"area":"lr"},{"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":"2605.26366","title":"Automatic Layer Selection for Hallucination Detection","created":"2026-05-25","cited_by_count":3,"area":null},{"id":"2606.10646","title":"How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs","created":"2026-06-09","cited_by_count":3,"area":"lr"},{"id":"2606.11599","title":"When is Your LLM Steerable?","created":"2026-06-10","cited_by_count":3,"area":"mechinterp"},{"id":"2411.09689","title":"Probing LLM Hallucination from Within: Perturbation-Driven Approach via Internal Knowledge","created":"2024-11-14","cited_by_count":2,"area":null},{"id":"2502.13490","title":"What are Models Thinking about? Understanding Large Language Model Hallucinations \"Psychology\" through Model Inner State Analysis","created":"2025-02-19","cited_by_count":2,"area":"lr"},{"id":"2503.11280","title":"High-Dimensional Interlingual Representations of Large Language Models","created":"2025-03-14","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":"2506.17748","title":"HIDE and Seek: Detecting Hallucinations in Language Models via Decoupled Representations","created":"2025-06-21","cited_by_count":2,"area":null},{"id":"2508.17767","title":"ISACL: Internal State Analyzer for Copyrighted Training Data Leakage","created":"2025-08-25","cited_by_count":2,"area":null},{"id":"2503.04615","title":"HalluCounter: Reference-free LLM Hallucination Detection in the Wild!","created":"2025-03-06","cited_by_count":1,"area":null},{"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":"2505.16526","title":"EnSToM: Enhancing Dialogue Systems with Entropy-Scaled Steering Vectors for Topic Maintenance","created":"2025-05-22","cited_by_count":1,"area":"mechinterp"},{"id":"2507.15903","title":"Towards Mitigation of Hallucination for LLM-empowered Agents: Progressive Generalization Bound Exploration and Watchdog Monitor","created":"2025-07-21","cited_by_count":1,"area":"agents"},{"id":"2510.21891","title":"Embedding Trust: Semantic Isotropy Predicts Nonfactuality in Long-Form Text Generation","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2510.23217","title":"Process Reward Models for Sentence-Level Verification of LVLM Radiology Reports","created":"2025-10-27","cited_by_count":1,"area":"lr"},{"id":"2602.05059","title":"Evaluating Large Language Models on Solved and Unsolved Problems in Graph Theory: Implications for Computing Education","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2604.02830","title":"GRADE: Probing Knowledge Gaps in LLMs through Gradient Subspace Dynamics","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2604.15741","title":"Learning Uncertainty from Sequential Internal Dispersion in Large Language Models","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2605.28123","title":"Risk-aware Selective Prompting for Hallucination Mitigation in Large Vision-Language Models","created":"2026-05-27","cited_by_count":1,"area":"mllm"},{"id":"2605.31220","title":"Shared Doubt: Zero-Shot Cross-Lingual Confidence Estimation for Language Models","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.00251","title":"Capability Self-Assessment in Large Language Models","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.21917","title":"Pre-Generation Hallucination Detection in Large Language Models via Soft-Target Attention Probing","created":"2026-06-20","cited_by_count":1,"area":null},{"id":"2506.04774","title":"Fine-Grained Interpretation of Political Opinions in Large Language Models","created":"2025-06-05","cited_by_count":0,"area":"mechinterp"},{"id":"2506.23136","title":"LLM-Assisted Question-Answering on Technical Documents Using Structured Data-Aware Retrieval Augmented Generation","created":"2025-06-29","cited_by_count":0,"area":"rag"},{"id":"2510.14925","title":"False Fixed Points: Kantian Feedback, Stable Miscalibration, and Representational Compression in LLMs","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2602.01897","title":"Internal Flow Signatures for Self-Checking and Refinement in LLMs","created":"2026-02-02","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":"2603.13911","title":"On the Tip of the Tongue: Why LLMs Hallucinate Answers They Can Decode","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2604.00445","title":"Towards Reliable Truth-Aligned Uncertainty Estimation in Large Language Models","created":"2026-04-01","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":"2606.20929","title":"Peeking Inside LLMs: Leveraging Internal Artifacts of LLMs for Enhancing Reliability in Legal Classification","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.24790","title":"Grad Detect: Gradient-Based Hallucination Detection in LLMs","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2608.00033","title":"SIRIN: A Unified Toolkit for Detecting Contextual Hallucinations in Retrieval-Augmented and Memory-Grounded LLM Systems","created":"2026-07-20","cited_by_count":0,"area":"rag"},{"id":"2608.13591","title":"Stable Miscalibration in Large Language Models: A Practical View of High-Confidence Errors","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2608.16353","title":"HalluTracer: Pre-Decoding Truthfulness Prediction via Depth-Averaged Probe-Logit","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.29781","title":"Hallucination Neurons and Where to Find Them: An Investigation into the existence of Hallucination Neurons","created":"2026-09-24","cited_by_count":0,"area":"alignment"},{"id":"2609.35387","title":"TRACE: Single-Pass Decoding-Trace Risk Localization for Generation Calibration","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38111","title":"From Routing Signals to Selective Review: Visual regrounding in MoE VLMs","created":"2026-09-29","cited_by_count":0,"area":"mllm"},{"id":"2609.39478","title":"Also Small Models Can Reasonably Self-Evaluate Their Confidence","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.00656","title":"Lingtai: What Concept Geometry Reveals--and Does Not Reveal--About LLM Inference","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}