Can LLMs and humans be friends? Uncovering factors affecting human-AI intimacy formation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Hong, Yeseon, Choi, Junhyuk, Kim, Minju, Kim, Bugeun
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915313666228224
author Hong, Yeseon
Choi, Junhyuk
Kim, Minju
Kim, Bugeun
author_facet Hong, Yeseon
Choi, Junhyuk
Kim, Minju
Kim, Bugeun
contents Large language models (LLMs) are increasingly being used in conversational roles, yet little is known about how intimacy emerges in human-LLM interactions. Although previous work emphasized the importance of self-disclosure in human-chatbot interaction, it is questionable whether gradual and reciprocal self-disclosure is also helpful in human-LLM interaction. Thus, this study examined three possible aspects contributing to intimacy formation: gradual self-disclosure, reciprocity, and naturalness. Study 1 explored the impact of mutual, gradual self-disclosure with 29 users and a vanilla LLM. Study 2 adopted self-criticism methods for more natural responses and conducted a similar experiment with 53 users. Results indicate that gradual self-disclosure significantly enhances perceived social intimacy, regardless of persona reciprocity. Moreover, participants perceived utterances generated with self-criticism as more natural compared to those of vanilla LLMs; self-criticism fostered higher intimacy in early stages. Also, we observed that excessive empathetic expressions occasionally disrupted immersion, pointing to the importance of response calibration during intimacy formation.
format Preprint
id arxiv_https___arxiv_org_abs_2505_24658
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Can LLMs and humans be friends? Uncovering factors affecting human-AI intimacy formation
Hong, Yeseon
Choi, Junhyuk
Kim, Minju
Kim, Bugeun
Human-Computer Interaction
H.5.2; I.2.7
Large language models (LLMs) are increasingly being used in conversational roles, yet little is known about how intimacy emerges in human-LLM interactions. Although previous work emphasized the importance of self-disclosure in human-chatbot interaction, it is questionable whether gradual and reciprocal self-disclosure is also helpful in human-LLM interaction. Thus, this study examined three possible aspects contributing to intimacy formation: gradual self-disclosure, reciprocity, and naturalness. Study 1 explored the impact of mutual, gradual self-disclosure with 29 users and a vanilla LLM. Study 2 adopted self-criticism methods for more natural responses and conducted a similar experiment with 53 users. Results indicate that gradual self-disclosure significantly enhances perceived social intimacy, regardless of persona reciprocity. Moreover, participants perceived utterances generated with self-criticism as more natural compared to those of vanilla LLMs; self-criticism fostered higher intimacy in early stages. Also, we observed that excessive empathetic expressions occasionally disrupted immersion, pointing to the importance of response calibration during intimacy formation.
title Can LLMs and humans be friends? Uncovering factors affecting human-AI intimacy formation
topic Human-Computer Interaction
H.5.2; I.2.7
url https://arxiv.org/abs/2505.24658