Dynamic Generation of Personalities with Large Language Models
MP3•Главная эпизода
Manage episode 415456461 series 2954468
Контент предоставлен Rob. Весь контент подкастов, включая эпизоды, графику и описания подкастов, загружается и предоставляется непосредственно компанией Rob или ее партнером по платформе подкастов. Если вы считаете, что кто-то использует вашу работу, защищенную авторским правом, без вашего разрешения, вы можете выполнить процедуру, описанную здесь https://ru.player.fm/legal.
In the realm of mimicking human deliberation, large language models (LLMs) show promising performance, thereby amplifying the importance of this research area. Deliberation is influenced by both logic and personality. However, previous studies predominantly focused on the logic of LLMs, neglecting the exploration of personality aspects. In this work, we introduce Dynamic Personality Generation (DPG), a dynamic personality generation method based on Hypernetworks. Initially, we embed the Big Five personality theory into GPT-4 to form a personality assessment machine, enabling it to evaluate characters' personality traits from dialogues automatically. We propose a new metric to assess personality generation capability based on this evaluation method. Then, we use this personality assessment machine to evaluate dialogues in script data, resulting in a personality-dialogue dataset. Finally, we fine-tune DPG on the personality-dialogue dataset. Experiments prove that DPG's personality generation capability is stronger after fine-tuning on this dataset than traditional fine-tuning methods, surpassing prompt-based GPT-4.
2024: Jianzhi Liu, Hexiang Gu, Tianyu Zheng, Liuyu Xiang, Huijia Wu, Jie Fu, Zhaofeng He
https://arxiv.org/pdf/2404.07084
…
continue reading
2024: Jianzhi Liu, Hexiang Gu, Tianyu Zheng, Liuyu Xiang, Huijia Wu, Jie Fu, Zhaofeng He
https://arxiv.org/pdf/2404.07084
285 эпизодов