Image de couverture de livre

SHARP: Unlocking Interactive Hallucination via Stance Transfer in Role-Playing LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kong, Chuyi, Luo, Ziyang, Lin, Hongzhan, Fan, Zhiyuan, Fan, Yaxin, Sun, Yuxi, Ma, Jing
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

REFLEX: Self-Refining Explainable Fact-Checking via Verdict-Anchored Style Control
par: Kong, Chuyi, et autres
Publié: (2025)

PlatoLM: Teaching LLMs in Multi-Round Dialogue via a User Simulator
par: Kong, Chuyi, et autres
Publié: (2023)

DiffCoT: Diffusion-styled Chain-of-Thought Reasoning in LLMs
par: Cao, Shidong, et autres
Publié: (2026)

LLM-Enhanced Multiple Instance Learning for Joint Rumor and Stance Detection with Social Context Information
par: Yang, Ruichao, et autres
Publié: (2025)

From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms
par: Luo, Jinghao, et autres
Publié: (2026)

Reinforcement Tuning for Detecting Stances and Debunking Rumors Jointly with Large Language Models
par: Yang, Ruichao, et autres
Publié: (2024)

Counterfactual Debating with Preset Stances for Hallucination Elimination of LLMs
par: Fang, Yi, et autres
Publié: (2024)

Explainable Ethical Assessment on Human Behaviors by Generating Conflicting Social Norms
par: Sun, Yuxi, et autres
Publié: (2025)

GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse
par: Lin, Hongzhan, et autres
Publié: (2024)

ScratchEval: Are GPT-4o Smarter than My Child? Evaluating Large Multimodal Models with Visual Programming Challenges
par: Fu, Rao, et autres
Publié: (2024)

CofiPara: A Coarse-to-fine Paradigm for Multimodal Sarcasm Target Identification with Large Multimodal Models
par: Lin, Hongzhan, et autres
Publié: (2024)

Towards Low-Resource Harmful Meme Detection with LMM Agents
par: Huang, Jianzhao, et autres
Publié: (2024)

AMR-Evol: Adaptive Modular Response Evolution Elicits Better Knowledge Distillation for Large Language Models in Code Generation
par: Luo, Ziyang, et autres
Publié: (2024)

MFC-Bench: Benchmarking Multimodal Fact-Checking with Large Vision-Language Models
par: Wang, Shengkang, et autres
Publié: (2024)

Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models
par: Lin, Hongzhan, et autres
Publié: (2024)

MemeArena: Automating Context-Aware Unbiased Evaluation of Harmfulness Understanding for Multimodal Large Language Models
par: Chen, Zixin, et autres
Publié: (2025)

HalluClean: A Unified Framework to Combat Hallucinations in LLMs
par: Zhao, Yaxin, et autres
Publié: (2025)

MM-CRITIC: A Holistic Evaluation of Large Multimodal Models as Multimodal Critique
par: Zeng, Gailun, et autres
Publié: (2025)

Self-Prompt Tuning: Enable Autonomous Role-Playing in LLMs
par: Kong, Aobo, et autres
Publié: (2024)

RoleBreak: Character Hallucination as a Jailbreak Attack in Role-Playing Systems
par: Tang, Yihong, et autres
Publié: (2024)

DRAG: Distilling RAG for SLMs from LLMs to Transfer Knowledge and Mitigate Hallucination via Evidence and Graph-based Distillation
par: Chen, Jennifer, et autres
Publié: (2025)

CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding?
par: Zhao, Yuwei, et autres
Publié: (2024)

Mitigating Hallucination in Fictional Character Role-Play
par: Sadeq, Nafis, et autres
Publié: (2024)

ClarityEthic: Explainable Moral Judgment Utilizing Contrastive Ethical Insights from Large Language Models
par: Sun, Yuxi, et autres
Publié: (2024)

Towards Comprehensive Stage-wise Benchmarking of Large Language Models in Fact-Checking
par: Lin, Hongzhan, et autres
Publié: (2026)

CodeHalu: Investigating Code Hallucinations in LLMs via Execution-based Verification
par: Tian, Yuchen, et autres
Publié: (2024)

AdamMeme: Adaptively Probe the Reasoning Capacity of Multimodal Large Language Models on Harmfulness
par: Chen, Zixin, et autres
Publié: (2025)

Acting Flatterers via LLMs Sycophancy: Combating Clickbait with LLMs Opposing-Stance Reasoning
par: Zhang, Chaowei, et autres
Publié: (2026)

CausalAbstain: Enhancing Multilingual LLMs with Causal Reasoning for Trustworthy Abstention
par: Sun, Yuxi, et autres
Publié: (2025)

Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules
par: Zhang, Yueqi, et autres
Publié: (2025)

SocialBench: Sociality Evaluation of Role-Playing Conversational Agents
par: Chen, Hongzhan, et autres
Publié: (2024)

CIP: A Plug-and-Play Causal Prompting Framework for Mitigating Hallucinations under Long-Context Noise
par: Ma, Qingsen, et autres
Publié: (2025)

Probabilistic Concept Graph Reasoning for Multimodal Misinformation Detection
par: Yang, Ruichao, et autres
Publié: (2026)

RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-Playing
par: Xiang, Hao, et autres
Publié: (2025)

Is External Information Useful for Stance Detection with LLMs?
par: Nguyen, Quang Minh, et autres
Publié: (2025)

Community-Aligned Behavior Under Uncertainty: Evidence of Epistemic Stance Transfer in LLMs
par: Gerard, Patrick, et autres
Publié: (2025)

Explainable Fake News Detection With Large Language Model via Defense Among Competing Wisdom
par: Wang, Bo, et autres
Publié: (2024)

H-Neurons: On the Existence, Impact, and Origin of Hallucination-Associated Neurons in LLMs
par: Gao, Cheng, et autres
Publié: (2025)

Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization
par: Tseng, Yu-Min, et autres
Publié: (2024)

Chain of Stance: Stance Detection with Large Language Models
par: Ma, Junxia, et autres
Publié: (2024)