SimsChat: A Customisable Persona-Driven Role-Playing Agent
- URL: http://arxiv.org/abs/2406.17962v2
- Date: Sun, 30 Jun 2024 21:15:47 GMT
- Title: SimsChat: A Customisable Persona-Driven Role-Playing Agent
- Authors: Bohao Yang, Dong Liu, Chen Tang, Chenghao Xiao, Kun Zhao, Chao Li, Lin Yuan, Guang Yang, Lanxiao Huang, Chenghua Lin,
- Abstract summary: Large Language Models (LLMs) possess the capability to understand human instructions and generate high-quality text.
We introduce the Customisable Conversation Agent Framework, which employs LLMs to simulate real-world characters.
We present SimsChat, a freely customisable role-playing agent.
- Score: 29.166067413153353
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Large Language Models (LLMs) possess the remarkable capability to understand human instructions and generate high-quality text, enabling them to act as agents that simulate human behaviours. This capability allows LLMs to emulate human beings in a more advanced manner, beyond merely replicating simple human behaviours. However, there is a lack of exploring into leveraging LLMs to craft characters from several aspects. In this work, we introduce the Customisable Conversation Agent Framework, which employs LLMs to simulate real-world characters that can be freely customised according to different user preferences. The customisable framework is helpful for designing customisable characters and role-playing agents according to human's preferences. We first propose the SimsConv dataset, which comprises 68 different customised characters, 1,360 multi-turn role-playing dialogues, and encompasses 13,971 interaction dialogues in total. The characters are created from several real-world elements, such as career, aspiration, trait, and skill. Building on these foundations, we present SimsChat, a freely customisable role-playing agent. It incorporates different real-world scenes and topic-specific character interaction dialogues, simulating characters' life experiences in various scenarios and topic-specific interactions with specific emotions. Experimental results show that our proposed framework achieves desirable performance and provides helpful guideline for building better simulacra of human beings in the future. Our data and code are available at https://github.com/Bernard-Yang/SimsChat.
Related papers
- AMONGAGENTS: Evaluating Large Language Models in the Interactive Text-Based Social Deduction Game [12.384945632524424]
This paper focuses on creating proxies of human behavior in simulated environments, with Among Us utilized as a tool for studying simulated human behavior.
Our work demonstrates that state-of-the-art large language models (LLMs) can effectively grasp the game rules and make decisions based on the current context.
arXiv Detail & Related papers (2024-07-23T14:34:38Z) - LLM Roleplay: Simulating Human-Chatbot Interaction [52.03241266241294]
LLM-Roleplay is a goal-oriented, persona-based method to automatically generate diverse multi-turn dialogues simulating human-chatbot interaction.
We collect natural human-chatbot dialogues from different sociodemographic groups and conduct a human evaluation to compare real human-chatbot dialogues with our generated dialogues.
arXiv Detail & Related papers (2024-07-04T14:49:46Z) - Capturing Minds, Not Just Words: Enhancing Role-Playing Language Models with Personality-Indicative Data [58.92110996840019]
We propose to enhance role-playing language models (RPLMs) via personality-indicative data.
Specifically, we leverage questions from psychological scales and distill advanced RPAs to generate dialogues that grasp the minds of characters.
Experimental results validate that RPLMs trained with our dataset exhibit advanced role-playing capabilities for both general and personality-related evaluations.
arXiv Detail & Related papers (2024-06-27T06:24:00Z) - CloChat: Understanding How People Customize, Interact, and Experience
Personas in Large Language Models [15.915071948354466]
CloChat is an interface supporting easy and accurate customization of agent personas in large language models.
Results indicate that participants formed emotional bonds with the customized agents, engaged in more dynamic dialogues, and showed interest in sustaining interactions.
arXiv Detail & Related papers (2024-02-23T11:25:17Z) - RoleCraft-GLM: Advancing Personalized Role-Playing in Large Language Models [6.753588449962107]
RoleCraft-GLM is an innovative framework aimed at enhancing personalized role-playing with Large Language Models (LLMs)
We contribute a unique conversational dataset that shifts from conventional celebrity-centric characters to diverse, non-celebrity personas.
Our approach includes meticulous character development, ensuring dialogues are both realistic and emotionally resonant.
arXiv Detail & Related papers (2023-12-17T17:57:50Z) - CharacterGLM: Customizing Chinese Conversational AI Characters with
Large Language Models [66.4382820107453]
We present CharacterGLM, a series of models built upon ChatGLM, with model sizes ranging from 6B to 66B parameters.
Our CharacterGLM is designed for generating Character-based Dialogues (CharacterDial), which aims to equip a conversational AI system with character customization for satisfying people's inherent social desires and emotional needs.
arXiv Detail & Related papers (2023-11-28T14:49:23Z) - Character-LLM: A Trainable Agent for Role-Playing [67.35139167985008]
Large language models (LLMs) can be used to serve as agents to simulate human behaviors.
We introduce Character-LLM that teach LLMs to act as specific people such as Beethoven, Queen Cleopatra, Julius Caesar, etc.
arXiv Detail & Related papers (2023-10-16T07:58:56Z) - Tachikuma: Understading Complex Interactions with Multi-Character and
Novel Objects by Large Language Models [67.20964015591262]
We introduce a benchmark named Tachikuma, comprising a Multiple character and novel Object based interaction Estimation task and a supporting dataset.
The dataset captures log data from real-time communications during gameplay, providing diverse, grounded, and complex interactions for further explorations.
We present a simple prompting baseline and evaluate its performance, demonstrating its effectiveness in enhancing interaction understanding.
arXiv Detail & Related papers (2023-07-24T07:40:59Z) - Generative Agents: Interactive Simulacra of Human Behavior [86.1026716646289]
We introduce generative agents--computational software agents that simulate believable human behavior.
We describe an architecture that extends a large language model to store a complete record of the agent's experiences.
We instantiate generative agents to populate an interactive sandbox environment inspired by The Sims.
arXiv Detail & Related papers (2023-04-07T01:55:19Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.