English

Multimodal Conversation Structure Understanding

Computation and Language 2026-01-29 v3

Abstract

While multimodal large language models (LLMs) excel at dialogue, whether they can adequately parse the structure of conversation -- conversational roles and threading -- remains underexplored. In this work, we introduce a suite of tasks and release TV-MMPC, a new annotated dataset, for multimodal conversation structure understanding. Our evaluation reveals that while all multimodal LLMs outperform our heuristic baseline, even the best-performing model we consider experiences a substantial drop in performance when character identities of the conversation are anonymized. Beyond evaluation, we carry out a sociolinguistic analysis of 350,842 utterances in TVQA. We find that while female characters initiate conversations at rates in proportion to their speaking time, they are 1.2 times more likely than men to be cast as an addressee or side-participant, and the presence of side-participants shifts the conversational register from personal to social.

Keywords

Cite

@article{arxiv.2505.17536,
  title  = {Multimodal Conversation Structure Understanding},
  author = {Kent K. Chang and Mackenzie Hanh Cramer and Anna Ho and Ti Ti Nguyen and Yilin Yuan and David Bamman},
  journal= {arXiv preprint arXiv:2505.17536},
  year   = {2026}
}

Comments

accepted to EACL 2026 main conference; 22 pages, 9 figures, 10 tables

R2 v1 2026-07-01T02:33:15.511Z