Image de couverture de livre

When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sun, Zhongxiang, Zhan, Yi, Shen, Chenglei, Yu, Weijie, Zhang, Xiao, He, Ming, Xu, Jun
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective
par: Sun, Zhongxiang, et autres
Publié: (2025)

Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm
par: Wang, Haoyu, et autres
Publié: (2026)

On the Decision-Making Abilities in Role-Playing using Large Language Models
par: Shen, Chenglei, et autres
Publié: (2024)

MAPS: Motivation-Aware Personalized Search via LLM-Driven Consultation Alignment
par: Qin, Weicong, et autres
Publié: (2025)

Multi-Personality Generation of LLMs at Decoding-time
par: Chen, Rongxin, et autres
Publié: (2025)

Mitigating Misleading Chain-of-Thought Reasoning with Selective Filtering
par: Wu, Yexin, et autres
Publié: (2024)

Orchestrating LLMs with Different Personalizations
par: Zhou, Jin Peng, et autres
Publié: (2024)

Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations
par: Yu, Lei, et autres
Publié: (2024)

Do LLMs Have Distinct and Consistent Personality? TRAIT: Personality Testset designed for LLMs with Psychometrics
par: Lee, Seungbeen, et autres
Publié: (2024)

Guided Profile Generation Improves Personalization with LLMs
par: Zhang, Jiarui
Publié: (2024)

Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation
par: Zhang, Xiaoying, et autres
Publié: (2024)

When Personalization Meets Reality: A Multi-Faceted Analysis of Personalized Preference Learning
par: Dong, Yijiang River, et autres
Publié: (2025)

FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning
par: Zhang, Zhehao, et autres
Publié: (2025)

KARL: Mitigating Hallucinations in LLMs via Knowledge-Boundary-Aware Reinforcement Learning
par: Gao, Cheng, et autres
Publié: (2026)

Advancing and Benchmarking Personalized Tool Invocation for LLMs
par: Huang, Xu, et autres
Publié: (2025)

EduAgentQG: A Multi-Agent Workflow Framework for Personalized Question Generation
par: Jia, Rui, et autres
Publié: (2025)

PAD: Personalized Alignment of LLMs at Decoding-Time
par: Chen, Ruizhe, et autres
Publié: (2024)

Hallucination Detection and Hallucination Mitigation: An Investigation
par: Luo, Junliang, et autres
Publié: (2024)

The Personalization Trap: How User Memory Alters Emotional Reasoning in LLMs
par: Fang, Xi, et autres
Publié: (2025)

Can Hallucinations Help? Boosting LLMs for Drug Discovery
par: Yuan, Shuzhou, et autres
Publié: (2025)

Balancing Stylization and Truth via Disentangled Representation Steering
par: Shen, Chenglei, et autres
Publié: (2025)

Selective Prompting Tuning for Personalized Conversations with LLMs
par: Huang, Qiushi, et autres
Publié: (2024)

Humanity in AI: Detecting the Personality of Large Language Models
par: Zhan, Baohua, et autres
Publié: (2024)

Is this the real life? Is this just fantasy? The Misleading Success of Simulating Social Interactions With LLMs
par: Zhou, Xuhui, et autres
Publié: (2024)

When Benchmarks Leak: Inference-Time Decontamination for LLMs
par: Chai, Jianzhe, et autres
Publié: (2026)

Hallucination is Inevitable for LLMs with the Open World Assumption
par: Xu, Bowen
Publié: (2025)

Unlocking Reasoning Capabilities in LLMs via Reinforcement Learning Exploration
par: Deng, Wenhao, et autres
Publié: (2025)

Improving Natural Language Understanding for LLMs via Large-Scale Instruction Synthesis
par: Yuan, Lin, et autres
Publié: (2025)

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace
par: Duan, Zenghao, et autres
Publié: (2025)

Aligning VLM Assistants with Personalized Situated Cognition
par: Li, Yongqi, et autres
Publié: (2025)

Personality-affected Emotion Generation in Dialog Systems
par: Wen, Zhiyuan, et autres
Publié: (2024)

A Personalized Conversational Benchmark: Towards Simulating Personalized Conversations
par: Li, Li, et autres
Publié: (2025)

Coarse-to-Fine Personalized LLM Impressions for Streamlined Radiology Reports
par: Sun, Chengbo, et autres
Publié: (2025)

HICD: Hallucination-Inducing via Attention Dispersion for Contrastive Decoding to Mitigate Hallucinations in Large Language Models
par: Jiang, Xinyan, et autres
Publié: (2025)

Generative Personality Simulation via Theory-Informed Structured Interview
par: Wang, Pengda, et autres
Publié: (2025)

How Good (Or Bad) Are LLMs at Detecting Misleading Visualizations?
par: Lo, Leo Yu-Ho, et autres
Publié: (2024)

Mitigating Hallucinations in Large Language Models via Causal Reasoning
par: Li, Yuangang, et autres
Publié: (2025)

AI PERSONA: Towards Life-long Personalization of LLMs
par: Wang, Tiannan, et autres
Publié: (2024)

ESG-Bench: Benchmarking Long-Context ESG Reports for Hallucination Mitigation
par: Sun, Siqi, et autres
Publié: (2026)

Sequence-Level Certainty Reduces Hallucination In Knowledge-Grounded Dialogue Generation
par: Wan, Yixin, et autres
Publié: (2023)