Cover Image

What are Models Thinking about? Understanding Large Language Model Hallucinations "Psychology" through Model Inner State Analysis

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Peiran, Liu, Yang, Lu, Yunfei, Hong, Jue, Wu, Ye
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Alleviating Hallucinations of Large Language Models through Induced Hallucinations
by: Zhang, Yue, et al.
Published: (2023)

Copy-Paste to Mitigate Large Language Model Hallucinations
by: Long, Yongchao, et al.
Published: (2025)

AgentArmor: Enforcing Program Analysis on Agent Runtime Trace to Defend Against Prompt Injection
by: Wang, Peiran, et al.
Published: (2025)

Hallucinate Less by Thinking More: Aspect-Based Causal Abstention for Large Language Models
by: Nguyen, Vy, et al.
Published: (2025)

Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models
by: Su, Weihang, et al.
Published: (2024)

Think Before You Speak: Cultivating Communication Skills of Large Language Models via Inner Monologue
by: Zhou, Junkai, et al.
Published: (2023)

Confabulation: The Surprising Value of Large Language Model Hallucinations
by: Sui, Peiqi, et al.
Published: (2024)

From Hallucinations to Jailbreaks: Rethinking the Vulnerability of Large Foundation Models
by: Jin, Haibo, et al.
Published: (2025)

Iter-AHMCL: Alleviate Hallucination for Large Language Model via Iterative Model-level Contrastive Learning
by: Wu, Huiwen, et al.
Published: (2024)

What if...?: Thinking Counterfactual Keywords Helps to Mitigate Hallucination in Large Multi-modal Models
by: Kim, Junho, et al.
Published: (2024)

Foot In The Door: Understanding Large Language Model Jailbreaking via Cognitive Psychology
by: Wang, Zhenhua, et al.
Published: (2024)

HICD: Hallucination-Inducing via Attention Dispersion for Contrastive Decoding to Mitigate Hallucinations in Large Language Models
by: Jiang, Xinyan, et al.
Published: (2025)

Enhancing Creativity in Large Language Models through Associative Thinking Strategies
by: Mehrotra, Pronita, et al.
Published: (2024)

What is an "Abstract Reasoner"? Revisiting Experiments and Arguments about Large Language Models
by: Yun, Tian, et al.
Published: (2025)

An Evolutionary Large Language Model for Hallucination Mitigation
by: Boulesnane, Abdennour, et al.
Published: (2024)

The Cost of Thinking: Increased Jailbreak Risk in Large Language Models
by: Yang, Fan
Published: (2025)

Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations
by: Yu, Lei, et al.
Published: (2024)

Multi-Persona Thinking for Bias Mitigation in Large Language Models
by: Chen, Yuxing, et al.
Published: (2026)

THiNK: Can Large Language Models Think-aloud?
by: Yu, Yongan, et al.
Published: (2025)

Understanding Privacy Risks of Embeddings Induced by Large Language Models
by: Zhu, Zhihao, et al.
Published: (2024)

Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Models
by: Lv, Qitan, et al.
Published: (2024)

CLAIM: Mitigating Multilingual Object Hallucination in Large Vision-Language Models with Cross-Lingual Attention Intervention
by: Ye, Zekai, et al.
Published: (2025)

ANAH: Analytical Annotation of Hallucinations in Large Language Models
by: Ji, Ziwei, et al.
Published: (2024)

The Impact of Negated Text on Hallucination with Large Language Models
by: Seo, Jaehyung, et al.
Published: (2025)

Theoretical Foundations and Mitigation of Hallucination in Large Language Models
by: Gumaan, Esmail
Published: (2025)

Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in?
by: Zhong, Chengzhi, et al.
Published: (2024)

Understanding the Dilemma of Unlearning for Large Language Models
by: Zhang, Qingjie, et al.
Published: (2025)

Attention-guided Self-reflection for Zero-shot Hallucination Detection in Large Language Models
by: Liu, Qiang, et al.
Published: (2025)

What Large Language Models Know and What People Think They Know
by: Steyvers, Mark, et al.
Published: (2024)

Maintaining Informative Coherence: Migrating Hallucinations in Large Language Models via Absorbing Markov Chains
by: Wu, Jiemin, et al.
Published: (2024)

MALM: A Multi-Information Adapter for Large Language Models to Mitigate Hallucination
by: Jia, Ao, et al.
Published: (2025)

Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Models
by: Chen, Yuyan, et al.
Published: (2024)

HalluSAE: Detecting Hallucinations in Large Language Models via Sparse Auto-Encoders
by: Chen, Boshui, et al.
Published: (2026)

Information Suppression in Large Language Models: Auditing, Quantifying, and Characterizing Censorship in DeepSeek
by: Qiu, Peiran, et al.
Published: (2025)

Beyond Facts: Evaluating Intent Hallucination in Large Language Models
by: Hao, Yijie, et al.
Published: (2025)

HALO: An Ontology for Representing and Categorizing Hallucinations in Large Language Models
by: Nananukul, Navapat, et al.
Published: (2023)

Reference-free Hallucination Detection for Large Vision-Language Models
by: Li, Qing, et al.
Published: (2024)

Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization
by: Chrysostomou, George, et al.
Published: (2023)

Neural Probe-Based Hallucination Detection for Large Language Models
by: Liang, Shize, et al.
Published: (2025)

Counterfactual Probing for Hallucination Detection and Mitigation in Large Language Models
by: Feng, Yijun
Published: (2025)