human-llm-interaction

This paper investigates syntactic convergence in instruction-tuned large language models, finding that they reuse human syntax more than humans themselves do in dialogue contexts, with instruction-tuning increasing reliance on syntactic patterns.

This paper introduces PersuasionTrace, a framework for studying multi-turn persuasion in human-LLM interaction, using a Bayesian-network simulated target that models belief updates. The framework reveals that LLMs are persuasive across topics and modalities, and that the Bayesian target better matches human belief dynamics than vanilla LLM simulators.

This paper studies how humans and large language models linguistically accommodate each other during multi-turn conversations, finding that LLMs overconverge to user style while humans accommodate LLMs no differently than humans.