September 5, 2025Cognitive ScienceOpen Access

Can Large Language Models Simulate Spoken Human Conversations?

View Full Paper

Ask AI

Bookmark

LLMs are proficient in chat‐based conversation but struggle with spoken conversation fidelity.
In Study 1, transcripts from LLMs showed exaggerated alignment compared to human conversations.
Study 2 found that humans could distinguish LLM transcripts from those of actual conversations.
Spoken conversations generated by LLMs differ qualitatively and quantitatively from human interactions.

Discussion

No takes yet. Share an insight, caveat, or question.

Comparative analysis reveals limitations of large language models in simulating spoken conversations.

Mayor et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark