Building Better AI Agents: A Provocation on the Utilisation of Persona in LLM-based Conversational Agents

TL;DR

This paper critically examines the use of personas in LLM-based conversational agents, discussing their benefits, challenges, ethical considerations, and the importance of maintaining consistency and effective evaluation.

Contribution

It provides a comprehensive analysis of persona integration in LLM-based CAs, emphasizing nuanced approaches and highlighting key challenges and ethical issues.

Findings

Persona consistency is crucial for user trust.

Effective evaluation mechanisms are needed for personalized CAs.

Ethical dilemmas must be addressed in persona design.

Abstract

The incorporation of Large Language Models (LLMs) such as the GPT series into diverse sectors including healthcare, education, and finance marks a significant evolution in the field of artificial intelligence (AI). The increasing demand for personalised applications motivated the design of conversational agents (CAs) to possess distinct personas. This paper commences by examining the rationale and implications of imbuing CAs with unique personas, smoothly transitioning into a broader discussion of the personalisation and anthropomorphism of CAs based on LLMs in the LLM era. We delve into the specific applications where the implementation of a persona is not just beneficial but critical for LLM-based CAs. The paper underscores the necessity of a nuanced approach to persona integration, highlighting the potential challenges and ethical dilemmas that may arise. Attention is directed towards the importance of maintaining persona consistency, establishing robust evaluation mechanisms, and ensuring that the persona attributes are effectively complemented by domain-specific knowledge.