Generative Language Models for Personality-Based Utterances in Novels: A Character Clustering Approach

초록

In novels, readers encounter a variety of characters with distinct personalities, and their satisfaction tends to increase when each character's utterances consistently reflect their unique traits. Recent advances in large language model (LLM) technology have made it possible to perform complex tasks such as generating long-form narratives and adapting writing styles. However, research on generating character utterances that reflect individual personalities remains limited. In this paper, we identify a key challenge in this task, namely the unconscious influence of the author's writing style, and propose a novel clustering-based method to mitigate this problem by tuning large language models. We manually annotated Big Five personality trait scores for characters appearing in selected novels and designed prompts to generate examples for instruction-tuning. Experimental results demonstrate that language models trained using our proposed method produce utterances that more consistently reflect character personalities compared to untuned models.

키워드