HonkaiChat: Companions from Anime that feel alive!

TL;DR

This paper introduces an event-driven dialogue framework for anime-themed chatbots that enhances engagement and naturalness by embedding dynamic events and fine-tuning models, demonstrating improved lifelike interactions.

Contribution

It presents a novel event-driven prompt approach combined with character-specific fine-tuning to create more dynamic and engaging anime chatbots.

Findings

Event-driven prompts improve conversational engagement

Enhanced naturalness and reduced hallucinations in chatbots

Effective application in Honkai: Star Rail context

Abstract

Modern conversational agents, including anime-themed chatbots, are frequently reactive and personality-driven but fail to capture the dynamic nature of human interactions. We propose an event-driven dialogue framework to address these limitations by embedding dynamic events in conversation prompts and fine-tuning models on character-specific data. Evaluations on GPT-4 and comparisons with industry-leading baselines demonstrate that event-driven prompts significantly improve conversational engagement and naturalness while reducing hallucinations. This paper explores the application of this approach in creating lifelike chatbot interactions within the context of Honkai: Star Rail, showcasing the potential for dynamic event-based systems to transform role-playing and interactive dialogue.