MINDECHO: Role-Playing Language Agents for Key Opinion Leaders
This addresses the demand for AI agents that mimic Internet celebrities to shape trends, but it is incremental as it builds on existing role-playing language agent methods.
The paper tackles the problem of creating role-playing language agents for Key Opinion Leaders (KOLs) by introducing MINDECHO, a framework that collects data from video transcripts and uses GPT-4 for conversation synthesis, with experiments validating its effectiveness in developing and evaluating such agents.
Large language models~(LLMs) have demonstrated impressive performance in various applications, among which role-playing language agents (RPLAs) have engaged a broad user base. Now, there is a growing demand for RPLAs that represent Key Opinion Leaders (KOLs), \ie, Internet celebrities who shape the trends and opinions in their domains. However, research in this line remains underexplored. In this paper, we hence introduce MINDECHO, a comprehensive framework for the development and evaluation of KOL RPLAs. MINDECHO collects KOL data from Internet video transcripts in various professional fields, and synthesizes their conversations leveraging GPT-4. Then, the conversations and the transcripts are used for individualized model training and inference-time retrieval, respectively. Our evaluation covers both general dimensions (\ie, knowledge and tones) and fan-centric dimensions for KOLs. Extensive experiments validate the effectiveness of MINDECHO in developing and evaluating KOL RPLAs.