English

Distinct social-linguistic processing between humans and large audio-language models: Evidence from model-brain alignment

Computation and Language 2025-10-28 v2 Neurons and Cognition

Abstract

Voice-based AI development faces unique challenges in processing both linguistic and paralinguistic information. This study compares how large audio-language models (LALMs) and humans integrate speaker characteristics during speech comprehension, asking whether LALMs process speaker-contextualized language in ways that parallel human cognitive mechanisms. We compared two LALMs' (Qwen2-Audio and Ultravox 0.5) processing patterns with human EEG responses. Using surprisal and entropy metrics from the models, we analyzed their sensitivity to speaker-content incongruency across social stereotype violations (e.g., a man claiming to regularly get manicures) and biological knowledge violations (e.g., a man claiming to be pregnant). Results revealed that Qwen2-Audio exhibited increased surprisal for speaker-incongruent content and its surprisal values significantly predicted human N400 responses, while Ultravox 0.5 showed limited sensitivity to speaker characteristics. Importantly, neither model replicated the human-like processing distinction between social violations (eliciting N400 effects) and biological violations (eliciting P600 effects). These findings reveal both the potential and limitations of current LALMs in processing speaker-contextualized language, and suggest differences in social-linguistic processing mechanisms between humans and LALMs.

Keywords

Cite

@article{arxiv.2503.19586,
  title  = {Distinct social-linguistic processing between humans and large audio-language models: Evidence from model-brain alignment},
  author = {Hanlin Wu and Xufeng Duan and Zhenguang Cai},
  journal= {arXiv preprint arXiv:2503.19586},
  year   = {2025}
}

Comments

Hanlin Wu, Xufeng Duan, and Zhenguang Cai. 2025. Distinct social-linguistic processing between humans and large audio-language models: Evidence from model-brain alignment. In Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics, pages 135-143, Albuquerque, New Mexico, USA. Association for Computational Linguistics. https://aclanthology.org/2025.cmcl-1.18/

R2 v1 2026-06-28T22:33:43.891Z