Augmenting Dialog with Think-Aloud Utterances for Modeling Individual Personality Traits by LLM
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917048829870080 |
|---|---|
| author | Ishikura, Seiya Yamada, Hiroaki Hiraoka, Tatsuya Yamada, Hiroaki Tokunaga, Takenobu |
| author_facet | Ishikura, Seiya Yamada, Hiroaki Hiraoka, Tatsuya Yamada, Hiroaki Tokunaga, Takenobu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_09158 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Augmenting Dialog with Think-Aloud Utterances for Modeling Individual Personality Traits by LLM Ishikura, Seiya Yamada, Hiroaki Hiraoka, Tatsuya Yamada, Hiroaki Tokunaga, Takenobu Computation and Language I.2.7 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. |
| title | Augmenting Dialog with Think-Aloud Utterances for Modeling Individual Personality Traits by LLM |
| topic | Computation and Language I.2.7 |
| url | https://arxiv.org/abs/2510.09158 |