Augmenting Dialog with Think-Aloud Utterances for Modeling Individual Personality Traits by LLM

2025/10/10 by Seiya Ishikura, Ishikura, Seiya, Tatsuya Hiraoka +5
Computer Science · #AI in Service Interactions #Computation and Language (cs.CL) #FOS: Computer and information sciences #I.2.7 #Speech and dialogue systems #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2510.09158

openalex publication_date 2025/10/10 · openalex created_date 2025/10/14 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data
• Personality Alignment of Large Language Models
• Gemma 2: Improving Open Language Models at a Practical Size
• Continual Pre-Training for Cross-Lingual LLM Adaptation: Enhancing Japanese Language Capabilities
• LARP: Language-Agent Role Play for Open-World Games
• Character-LLM: A Trainable Agent for Role-Playing
• RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models
• Self-Assessment Tests are Unreliable Measures of LLM Personality
• Have Large Language Models Developed a Personality?: Applicability of Self-Assessment Tests in Measuring Personality in LLMs
• QLoRA: Efficient Finetuning of Quantized LLMs
• PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits
• BERTScore: Evaluating Text Generation with BERT
• Personalizing Dialogue Agents: I have a dog, do you have pets too?
• An Introduction to the Five‐Factor Model and Its Applications

Related

• BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data
• Beyond Discrete Personas: Personality Modeling Through Journal Intensive Conversations
• Exploring the Potential of Large Language Models to Simulate Personality
• PersonalityChat: Conversation Distillation for Personalized Dialog Modeling with Facts and Traits
• Orca: Enhancing Role-Playing Abilities of Large Language Models by Integrating Personality Traits