Image de couverture de livre

The Rise of Darkness: Safety-Utility Trade-Offs in Role-Playing Dialogue Agents

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Tang, Yihong, Chen, Kehai, Bai, Xuefeng, Niu, Zhengyu, Wang, Bo, Liu, Jie, Zhang, Min
Format:	Preprint
Publié:	2025
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

Through the Lens of Character: Resolving Modality-Role Interference in Multimodal Role-Playing Agent
par: Tang, Yihong, et autres
Publié: (2026)

Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoning
par: Tang, Yihong, et autres
Publié: (2025)

Character-R1: Enhancing Role-Aware Reasoning in Role-Playing Agents via RLVR
par: Tang, Yihong, et autres
Publié: (2026)

The Power of Personality: A Human Simulation Perspective to Investigate Large Language Model Agents
par: Duan, Yifan, et autres
Publié: (2025)

CRPO: Character-centric Group Relative Policy Optimization for Role-aware Reasoning in Role-playing Agents
par: Tang, Yihong, et autres
Publié: (2026)

MASTER: Enhancing Large Language Model via Multi-Agent Simulated Teaching
par: Yue, Liang, et autres
Publié: (2025)

Beyond Token-Level Policy Gradients for Complex Reasoning with Large Language Models
par: Xu, Mufan, et autres
Publié: (2026)

Exploring Safety-Utility Trade-Offs in Personalized Language Models
par: Vijjini, Anvesh Rao, et autres
Publié: (2024)

ORPP: Self-Optimizing Role-playing Prompts to Enhance Language Model Capabilities
par: Duan, Yifan, et autres
Publié: (2025)

Efficient Safety Alignment of Large Language Models via Preference Re-ranking and Representation-based Reward Modeling
par: Deng, Qiyuan, et autres
Publié: (2025)

Generator-Assistant Stepwise Rollback Framework for Large Language Model Agent
par: Li, Xingzuo, et autres
Publié: (2025)

Agentic Tool Use in Large Language Models
par: Hu, Jinchao, et autres
Publié: (2026)

ERABAL: Enhancing Role-Playing Agents through Boundary-Aware Learning
par: Tang, Yihong, et autres
Publié: (2024)

Evaluating and Improving Cultural Awareness of Reward Models for LLM Alignment
par: Zhang, Hongbin, et autres
Publié: (2025)

Paying More Attention to Source Context: Mitigating Unfaithful Translations from Large Language Model
par: Zhang, Hongbin, et autres
Publié: (2024)

LinguaLIFT: An Effective Two-stage Instruction Tuning Framework for Low-Resource Language Reasoning
par: Zhang, Hongbin, et autres
Publié: (2024)

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

Exploring the Translation Mechanism of Large Language Models
par: Zhang, Hongbin, et autres
Publié: (2025)

Question-guided Knowledge Graph Re-scoring and Injection for Knowledge Graph Question Answering
par: Zhang, Yu, et autres
Publié: (2024)

Constituency Parsing using LLMs
par: Bai, Xuefeng, et autres
Publié: (2023)

LLM-based Discriminative Reasoning for Knowledge Graph Question Answering
par: Xu, Mufan, et autres
Publié: (2024)

HITSZ's End-To-End Speech Translation Systems Combining Sequence-to-Sequence Auto Speech Recognition Model and Indic Large Language Model for IWSLT 2025 in Indic Track
par: Wei, Xuchen, et autres
Publié: (2025)

MORPHEUS: Modeling Role from Personalized Dialogue History by Exploring and Utilizing Latent Space
par: Tang, Yihong, et autres
Publié: (2024)

TF-Attack: Transferable and Fast Adversarial Attacks on Large Language Models
par: Li, Zelin, et autres
Publié: (2024)

Mitigating Multimodal Hallucination via Phase-wise Self-reward
par: Zhang, Yu, et autres
Publié: (2026)

Instruction Anchor: Dissecting the Mechanistic Dynamics of Modality Arbitration
par: Zhang, Yu, et autres
Publié: (2026)

Beyond Unimodal Shortcuts: MLLMs as Cross-Modal Reasoners for Grounded Named Entity Recognition
par: Ma, Jinlong, et autres
Publié: (2026)

SafeSearch: Do Not Trade Safety for Utility in LLM Search Agents
par: Zhan, Qiusi, et autres
Publié: (2025)

Benchmarking and Improving Large Vision-Language Models for Fundamental Visual Graph Understanding and Reasoning
par: Zhu, Yingjie, et autres
Publié: (2024)

Adaptive Inner Speech-Text Alignment for LLM-based Speech Translation
par: Liu, Henglyu, et autres
Publié: (2025)

SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking
par: Huang, Weiyang, et autres
Publié: (2026)

RoleRMBench & RoleRM: Towards Reward Modeling for Profile-Based Role Play in Dialogue Systems
par: Ding, Hang, et autres
Publié: (2025)

MOOM: Maintenance, Organization and Optimization of Memory in Ultra-Long Role-Playing Dialogues
par: Chen, Weishu, et autres
Publié: (2025)

Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey
par: Qu, Bingzheng, et autres
Publié: (2026)

Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure
par: Li, Zirui, et autres
Publié: (2026)

User-Aware Active Knowledge Acquisition for Emotional Support Dialogue
par: Xu, Mufan, et autres
Publié: (2026)

Evaluating and Steering Modality Preferences in Multimodal Large Language Model
par: Zhang, Yu, et autres
Publié: (2025)

XIFBench: Evaluating Large Language Models on Multilingual Instruction Following
par: Li, Zhenyu, et autres
Publié: (2025)

PsyPlay: Personality-Infused Role-Playing Conversational Agents
par: Yang, Tao, et autres
Publié: (2025)

DUAL-REFLECT: Enhancing Large Language Models for Reflective Translation through Dual Learning Feedback Mechanisms
par: Chen, Andong, et autres
Publié: (2024)