Large Language Models ↔ role-playing

Relations (1)

related 2.00 — strongly supporting 3 facts

Large Language Models are directly linked to role-playing through frameworks designed to enhance these specific capabilities [1], academic surveys exploring persona-based interactions within LLMs [2], and the observation that model hallucinations can function as a creative asset during role-playing tasks [3].

Facts (3)

Sources

A Survey of Incorporating Psychological Theories in LLMs - arXiv arxiv.org arXiv 2 facts

referenceNoah Wang et al. introduced 'RoleLLM', a framework for benchmarking, eliciting, and enhancing the role-playing abilities of large language models.

referenceYu-Min Tseng, Yu-Chao Huang, Teng-Yun Hsiao, Wei-Lin Chen, Chao-Wei Huang, Yu Meng, and Yun-Nung Chen authored 'Two tales of persona in LLMs: A survey of role-playing and personalization', published in the Findings of the Association for Computational Linguistics: EMNLP 2024, pages 16612–16631, in Miami, Florida, USA, in November 2024.

The Role of Hallucinations in Large Language Models - CloudThat cloudthat.com CloudThat 1 fact

claimHallucinations in large language models can serve as a creative asset in contexts such as creative writing, brainstorming, roleplaying, prototype generation, and art or music creation.