{"total":79,"rows":[{"id":"2409.17504","title":"HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection","created":"2024-09-26","cited_by_count":99,"area":null},{"id":"2402.17811","title":"TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space","created":"2024-02-27","cited_by_count":91,"area":null},{"id":"2403.05612","title":"Unfamiliar Finetuning Examples Control How Language Models Hallucinate","created":"2024-03-08","cited_by_count":87,"area":"alignment"},{"id":"2411.19943","title":"Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability","created":"2024-11-29","cited_by_count":83,"area":"lr"},{"id":"2402.09267","title":"Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation","created":"2024-02-14","cited_by_count":80,"area":"alignment"},{"id":"2402.03190","title":"Unified Hallucination Detection for Multimodal Large Language Models","created":"2024-02-05","cited_by_count":75,"area":"mllm"},{"id":"2405.09719","title":"Spectral Editing of Activations for Large Language Model Alignment","created":"2024-05-15","cited_by_count":56,"area":"alignment"},{"id":"2404.17287","title":"When to Trust LLMs: Aligning Confidence with Response Quality","created":"2024-04-26","cited_by_count":43,"area":null},{"id":"2405.15116","title":"Quantifying the Gain in Weak-to-Strong Generalization","created":"2024-05-24","cited_by_count":41,"area":null},{"id":"2409.06857","title":"What is the Role of Small Models in the LLM Era: A Survey","created":"2024-09-10","cited_by_count":41,"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":"2503.15888","title":"Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models","created":"2025-03-20","cited_by_count":39,"area":"rag"},{"id":"2405.11613","title":"Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts","created":"2024-05-19","cited_by_count":36,"area":null},{"id":"2407.08039","title":"Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Models","created":"2024-07-10","cited_by_count":25,"area":null},{"id":"2410.18860","title":"DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations","created":"2024-10-24","cited_by_count":25,"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":"2409.18786","title":"A Survey on the Honesty of Large Language Models","created":"2024-09-27","cited_by_count":23,"area":"alignment"},{"id":"2501.01926","title":"Cross-Modal Attention Calibration for LVLM Hallucination Mitigation","created":"2025-01-03","cited_by_count":23,"area":"mllm"},{"id":"2405.12701","title":"OLAPH: Improving Factuality in Biomedical Long-form Question Answering","created":"2024-05-21","cited_by_count":20,"area":null},{"id":"2405.14383","title":"Perception of Knowledge Boundary for Large Language Models through Semi-open-ended Question Answering","created":"2024-05-23","cited_by_count":20,"area":null},{"id":"2408.12325","title":"Improving Factuality in Large Language Models via Decoding-Time Hallucinatory and Truthful Comparators","created":"2024-08-22","cited_by_count":19,"area":null},{"id":"2405.13432","title":"Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction","created":"2024-05-22","cited_by_count":18,"area":"alignment"},{"id":"2404.00216","title":"Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness","created":"2024-03-30","cited_by_count":17,"area":null},{"id":"2411.02433","title":"SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models","created":"2024-11-01","cited_by_count":16,"area":"moe"},{"id":"2505.15710","title":"Advancing LLM Safe Alignment with Safety Representation Ranking","created":"2025-05-21","cited_by_count":16,"area":"safety"},{"id":"2403.14401","title":"Pensieve: Retrospect-then-Compare Mitigates Visual Hallucination","created":"2024-03-21","cited_by_count":14,"area":"mllm"},{"id":"2406.12468","title":"Adaptive Token Biaser: Knowledge Editing via Biasing Key Entities","created":"2024-06-18","cited_by_count":14,"area":null},{"id":"2407.21057","title":"Multi-group Uncertainty Quantification for Long-form Text Generation","created":"2024-07-25","cited_by_count":13,"area":null},{"id":"2404.13752","title":"Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models","created":"2024-04-21","cited_by_count":12,"area":"mechinterp"},{"id":"2411.01610","title":"Explaining and Improving Contrastive Decoding by Extrapolating the Probabilities of a Huge and Hypothetical LM","created":"2024-11-03","cited_by_count":11,"area":null},{"id":"2504.17480","title":"Unified attacks to large language model watermarks: spoofing and scrubbing in unauthorized knowledge distillation","created":"2025-04-24","cited_by_count":11,"area":"safety"},{"id":"2403.19113","title":"FACTOID: FACtual enTailment fOr hallucInation Detection","created":"2024-03-28","cited_by_count":10,"area":null},{"id":"2402.17982","title":"Collaborative decoding of critical tokens for boosting factuality of large language models","created":"2024-02-28","cited_by_count":9,"area":null},{"id":"2408.05094","title":"Unlocking Decoding-time Controllability: Gradient-Free Multi-Objective Alignment with Contrastive Prompts","created":"2024-08-09","cited_by_count":9,"area":"alignment"},{"id":"2410.08970","title":"NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language Models","created":"2024-10-11","cited_by_count":9,"area":null},{"id":"2510.04398","title":"SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations","created":"2025-10-05","cited_by_count":9,"area":null},{"id":"2601.20279","title":"Hallucination Begins Where Saliency Drops","created":"2026-01-28","cited_by_count":9,"area":"mllm"},{"id":"2408.01916","title":"MAO: A Framework for Process Model Generation with Multi-Agent Orchestration","created":"2024-08-04","cited_by_count":8,"area":"agents"},{"id":"2409.06485","title":"Mitigating Hallucination in Visual-Language Models via Re-Balancing Contrastive Decoding","created":"2024-09-10","cited_by_count":8,"area":"mllm"},{"id":"2503.03032","title":"SAFE: A Sparse Autoencoder-Based Framework for Robust Query Enrichment and Hallucination Mitigation in LLMs","created":"2025-03-04","cited_by_count":8,"area":"mechinterp"},{"id":"2406.16069","title":"FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language Models","created":"2024-06-23","cited_by_count":7,"area":null},{"id":"2502.03199","title":"Improve Decoding Factuality by Token-wise Cross Layer Entropy of Large Language Models","created":"2025-02-05","cited_by_count":7,"area":null},{"id":"2503.12908","title":"HICD: Hallucination-Inducing via Attention Dispersion for Contrastive Decoding to Mitigate Hallucinations in Large Language Models","created":"2025-03-17","cited_by_count":7,"area":null},{"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":"2604.15574","title":"Why Fine-Tuning Encourages Hallucinations and How to Fix It","created":"2026-04-16","cited_by_count":7,"area":"distill"},{"id":"2504.18114","title":"Evaluating Evaluation Metrics -- The Mirage of Hallucination Detection","created":"2025-04-25","cited_by_count":6,"area":null},{"id":"2507.05288","title":"A Survey on Proactive Defense Strategies Against Misinformation in Large Language Models","created":"2025-07-05","cited_by_count":6,"area":null},{"id":"2407.05474","title":"Enhancing Hallucination Detection through Perturbation-Based Synthetic Data Generation in System Responses","created":"2024-07-07","cited_by_count":5,"area":"synth"},{"id":"2409.09947","title":"Gaps or Hallucinations? Gazing into Machine-Generated Legal Analysis for Fine-grained Text Evaluations","created":"2024-09-16","cited_by_count":4,"area":null},{"id":"2502.19127","title":"Exploring the Generalizability of Factual Hallucination Mitigation via Enhancing Precise Knowledge Utilization","created":"2025-02-26","cited_by_count":4,"area":null},{"id":"2505.17089","title":"Chain-of-Thought Driven Adversarial Scenario Extrapolation for Robust Language Models","created":"2025-05-20","cited_by_count":4,"area":"lr"},{"id":"2505.17870","title":"Just as Humans Need Vaccines, So Do Models: Model Immunization to Combat Falsehoods","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2507.04404","title":"LayerCake: Token-Aware Contrastive Decoding within Large Language Model Layers","created":"2025-07-06","cited_by_count":3,"area":null},{"id":"2602.20696","title":"PromptCD: Test-Time Behavior Enhancement via Polarity-Prompt Contrastive Decoding","created":"2026-02-24","cited_by_count":3,"area":null},{"id":"2410.19485","title":"A Debate-Driven Experiment on LLM Hallucinations and Accuracy","created":"2024-10-25","cited_by_count":2,"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":"2506.02696","title":"Shaking to Reveal: Perturbation-Based Detection of LLM Hallucinations","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2508.02184","title":"Retrieval-augmented Decoding for Improving Truthfulness in Open-ended Generation","created":"2025-08-04","cited_by_count":2,"area":"rag"},{"id":"2510.07884","title":"Contrastive Weak-to-strong Generalization","created":"2025-10-09","cited_by_count":2,"area":"alignment"},{"id":"2510.21883","title":"Language Ranker: A Lightweight Ranking framework for LLM Decoding","created":"2025-10-23","cited_by_count":2,"area":"alignment"},{"id":"2607.20426","title":"Knowledge Injection Exists in MoE? Exploring Expert-Aware Contrast Decoding in MoE for Mitigating LLMs'Hallucinations","created":"2026-05-08","cited_by_count":2,"area":"moe"},{"id":"2406.16377","title":"On the Transformations across Reward Model, Parameter Update, and In-Context Prompt","created":"2024-06-24","cited_by_count":1,"area":"alignment"},{"id":"2504.03302","title":"Noise Augmented Fine Tuning for Mitigating Hallucinations in Large Language Models","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2506.02973","title":"Expanding before Inferring: Enhancing Factuality in Large Language Models through Premature Layers Interpolation","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2510.13315","title":"Self-Aug: Query and Entropy Adaptive Decoding for Large Vision-Language Models","created":"2025-10-15","cited_by_count":1,"area":"mllm"},{"id":"2605.05953","title":"Hallucination as an Anomaly: Dynamic Intervention via Probabilistic Circuits","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.12813","title":"REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2410.00363","title":"Unleashing the Potentials of Likelihood Composition for Multi-modal Language Models","created":"2024-10-01","cited_by_count":0,"area":"mllm"},{"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":"2509.13702","title":"DSCC-HS: A Dynamic Self-Reinforcing Framework for Hallucination Suppression in Large Language Models","created":"2025-09-17","cited_by_count":0,"area":null},{"id":"2601.01156","title":"DHI: Leveraging Diverse Hallucination Induction for Enhanced Contrastive Factuality Control in Large Language Models","created":"2026-01-03","cited_by_count":0,"area":null},{"id":"2601.21744","title":"Temporal Guidance for Large Language Models","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.02258","title":"Alignment-Aware Model Adaptation via Feedback-Guided Optimization","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.20332","title":"No One Size Fits All: QueryBandits for Hallucination Mitigation","created":"2026-02-23","cited_by_count":0,"area":"lr"},{"id":"2604.13538","title":"Synthesizing Instruction-Tuning Datasets with Contrastive Decoding","created":"2026-04-15","cited_by_count":0,"area":"synth"},{"id":"2604.15789","title":"A Systematic Study of Training-Free Methods for Trustworthy Large Language Models","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2606.13171","title":"NTS-CoT: Mitigating Hallucinations in LLM-based News Timeline Summarization with Chain-of-Thought Reasoning","created":"2026-06-11","cited_by_count":0,"area":"lr"},{"id":"2609.15745","title":"Look Before You Leap: Factual Decoding with Internal Attribution Signals","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2610.18173","title":"TRACESTEER: Trace Driven Activation Steering for Hallucination Mitigation in Diffusion Language Models","created":"2026-10-13","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}