Can Large Language Models Simulate Spoken Human Conversations

Dados Bibliográficos

ID7150358
AutoresEric Mayor (0000-0001-9441-7592, Department of Psychology University of Basel, autor correspondente), Lucas M Bietti, Lucas Bietti (0000-0002-4380-2615, Department of Psychology Norwegian University of Science and Technology), Adrian Bangerter (0000-0003-3622-1860)
Ano2025
Volume49
Fascículo9
Páginase70106-e70106
Data de publicação2025-09-01
Peer ReviewedSim
Open AccessSim
TipoARTICLE
PeriódicoCognitive Science (JOURNAL)
Identificadores do periódicoISSN: 0364-0213 • E-ISSN: 1551-6709
EditoraWiley (PUBLISHER • GB)
DOI10.1111/cogs.70106
PMID40889249
OpenAlexW4413893334
IdiomaEN
Citações recebidas1
Referências citadas64

Large language models (LLMs) can emulate many aspects of human cognition and have been heralded as a potential paradigm shift. They are proficient in chat‐based conversation, but little is known about their ability to simulate spoken conversation. We investigated whether LLMs can simulate spoken human conversation. In Study 1, we compared transcripts of human telephone conversations from the Switchboard (SB) corpus to six corpora of transcripts generated by two powerful LLMs, GPT‐4 and Claude Sonnet 3.5, and two open‐source LLMs, Vicuna and Wayfarer, using different prompts designed to mimic SB participants’ instructions. We compared LLM and SB conversations in terms of alignment (conceptual, syntactic, and lexical), coordination markers, and coordination of openings and closings. We also documented qualitative features by which LLM conversations differ from SB conversations. In Study 2, we assessed whether humans can distinguish transcripts produced by LLMs from those of SB conversations. LLM conversations exhibited exaggerated alignment (and an increase in alignment as conversation unfolded) relative to human conversations, different and often inappropriate use of coordination markers, and were dissimilar to human conversations in openings and closings. LLM conversations did not consistently pass for SB conversations. Spoken conversations generated by LLMs are both qualitatively and quantitatively different from those of humans. This issue may evolve with better LLMs and more training on spoken conversation, but may also result from key differences between spoken conversation and chat

Conversation · Linguistics · Natural language processing · Spoken language · Communication · Computer Science · Natural Language Processing Techniques · Psychology · Speech and dialogue systems · Topic Modeling