Too Good to be Bad: On the Failure of LLMs to Role-Play Villains

Documenti analoghi

• BatonVoice: An Operationalist Framework for Enhancing Controllable Speech Synthesis with Linguistic Intelligence from LLMs
  di: Wang, Yue, et al.
  Pubblicazione: (2025)
• The Hunger Game Debate: On the Emergence of Over-Competition in Multi-Agent Systems
  di: Ma, Xinbei, et al.
  Pubblicazione: (2025)
• Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models
  di: Zhang, Bang, et al.
  Pubblicazione: (2025)
• Social Welfare Function Leaderboard: When LLM Agents Allocate Social Welfare
  di: Shi, Zhengliang, et al.
  Pubblicazione: (2025)
• CogDual: Enhancing Dual Cognition of LLMs via Reinforcement Learning with Implicit Rule-Based Rewards
  di: Liu, Cheng, et al.
  Pubblicazione: (2025)