用说话前的内心独白增强对话数据，让大模型更像真人
Augmenting Dialog with Think-Aloud Utterances for Modeling Individual Personality Traits by LLM
- 在对话中加入说话前的内心独白，提升模型对人格的模仿能力
- 加入内心独白后，模型在宜人性和神经质维度上更贴近真实人类
- 内心独白质量直接影响模型表现，适合人格建模研究者
本研究提出通过在文本对话中加入说话前的内心独白（Think-Aloud Utterances, TAU）来增强对话数据，以更好建模个体人格特征。TAU是说话人表达话语前的思维外化。我们假设使用TAU增强数据训练的“人格大模型”（persona LLM）能更准确地模拟说话者的个性特质。实验检验了这些模型在五大性格特质（Big Five）框架下是否与人类性格一致。结果表明，使用TAU增强数据训练的模型，在宜人性（Agreeableness）和神经质（Neuroticism）维度上比仅用原始对话数据训练的模型更接近真实说话者。同时发现，TAU增广的质量显著影响人格模型的表现。
原文摘要 · Abstract (English)
This study proposes augmenting dialog data with think-aloud utterances (TAUs) for modeling individual personalities in text chat by LLM. TAU is a verbalization of a speaker's thought before articulating the utterance. We expect "persona LLMs" trained with TAU-augmented data can mimic the speaker's personality trait better. We tested whether the trained persona LLMs obtain the human personality with respect to Big Five, a framework characterizing human personality traits from five aspects. The results showed that LLMs trained with TAU-augmented data more closely align to the speakers' Agreeableness and Neuroticism of Big Five than those trained with original dialog data. We also found that the quality of TAU-augmentation impacts persona LLM's performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。