CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Models

• URL: http://arxiv.org/abs/2311.16832v1
• Date: Tue, 28 Nov 2023 14:49:23 GMT
• Title: CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Models
• Authors: Jinfeng Zhou, Zhuang Chen, Dazhen Wan, Bosi Wen, Yi Song, Jifan Yu, Yongkang Huang, Libiao Peng, Jiaming Yang, Xiyao Xiao, Sahand Sabour, Xiaohan Zhang, Wenjing Hou, Yijia Zhang, Yuxiao Dong, Jie Tang, Minlie Huang
• Abstract summary: 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.
• Score: 66.4382820107453
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, 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. On top of CharacterGLM, we can customize various AI characters or social agents by configuring their attributes (identities, interests, viewpoints, experiences, achievements, social relationships, etc.) and behaviors (linguistic features, emotional expressions, interaction patterns, etc.). Our model outperforms most mainstream close-source large langauge models, including the GPT series, especially in terms of consistency, human-likeness, and engagement according to manual evaluations. We will release our 6B version of CharacterGLM and a subset of training data to facilitate further research development in the direction of character-based dialogue generation.

Related papers

• LLM Roleplay: Simulating Human-Chatbot Interaction [52.03241266241294]
  We propose a goal-oriented, persona-based method to automatically generate diverse multi-turn dialogues simulating human-chatbot interaction. Our method can simulate human-chatbot dialogues with a high indistinguishability rate.
  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)
• Crafting Customisable Characters with LLMs: Introducing SimsChat, a Persona-Driven Role-Playing Agent Framework [29.166067413153353]
  Large Language Models (LLMs) can comprehend human instructions and generate high-quality text. We introduce the Customisable Conversation Agent Framework, which leverages LLMs to simulate real-world characters. We present SimsChat, a freely customisable role-playing agent.
  arXiv  Detail & Related papers  (2024-06-25T22:44:17Z)
• 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)
• BotChat: Evaluating LLMs' Capabilities of Having Multi-Turn Dialogues [72.65163468440434]
  This report provides a preliminary evaluation of existing large language models for human-style multi-turn chatting. We prompt large language models (LLMs) to generate a full multi-turn dialogue based on the ChatSEED, utterance by utterance. We find GPT-4 can generate human-style multi-turn dialogues with impressive quality, significantly outperforms its counterparts.
  arXiv  Detail & Related papers  (2023-10-20T16:53:51Z)
• Enhancing Personalized Dialogue Generation with Contrastive Latent Variables: Combining Sparse and Dense Persona [16.90863217077699]
  Existing personalized dialogue agents model persona profiles from three resources: sparse or dense persona descriptions and dialogue histories. We combine the advantages of the three resources to obtain a richer and more accurate persona. Experimental results on Chinese and English datasets demonstrate our model's superiority in personalization.
  arXiv  Detail & Related papers  (2023-05-19T07:24:27Z)
• Hi Sheldon! Creating Deep Personalized Characters from TV Shows [52.8086853239762]
  We propose a novel task, named Deep Personalized Character Creation (DPCC), creating multimodal chat personalized characters from multimodal data such as TV shows. Given a single- or multi-modality input (text, audio, video), the goal of DPCC is to generate a multi-modality (text, audio, video) response. To support this novel task, we further collect a character centric multimodal dialogue dataset, named Deep Personalized Character dataset (DPCD), from TV shows. DPCD contains character-specific multimodal dialogue data of 10k utterances and 6 hours of audio/
  arXiv  Detail & Related papers  (2023-04-09T00:39:43Z)
• Large Language Models Meet Harry Potter: A Bilingual Dataset for Aligning Dialogue Agents with Characters [70.84938803753062]
  We introduce the Harry Potter Dialogue dataset, designed to advance the study of dialogue agents and character alignment. The dataset encompasses all dialogue sessions (in both English and Chinese) from the Harry Potter series. It is annotated with vital background information, including dialogue scenes, speakers, character relationships, and attributes.
  arXiv  Detail & Related papers  (2022-11-13T10:16:39Z)
• Estimating the Personality of White-Box Language Models [0.589889361990138]
  Large-scale language models, which are trained on large corpora of text, are being used in a wide range of applications everywhere. Existing research shows that these models can and do capture human biases. Many of these biases, especially those that could potentially cause harm, are being well-investigated. However, studies that infer and change human personality traits inherited by these models have been scarce or non-existent.
  arXiv  Detail & Related papers  (2022-04-25T23:53:53Z)

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.