M3-SLU: Evaluating Speaker-Attributed Reasoning in Multimodal Large Language Models

Yejin Kwon, Taewoo Kang, Hyunsoo Yoon, Chang Ouk Kim


Abstract
We present M3-SLU, a new multimodal large language model (MLLM) benchmark for evaluating multi-speaker, multi-turn spoken language understanding. While recent models show strong performance in speech and text comprehension, they still struggle with speaker-attributed reasoning, the ability to understand who said what and when in natural conversations. M3-SLU is built from four open corpora (CHiME-6, MELD, MultiDialog, and AMI) and comprises over 12,000 validated instances with paired audio, transcripts, and metadata. It includes two tasks: (1) Speaker-Attributed Question Answering and (2) Speaker Attribution via Utterance Matching. We provide baseline results for both cascaded pipelines and end-to-end MLLMs, evaluated using an LLM-as-Judge and accuracy metrics. Results show that while models can capture what was said, they often fail to identify who said it, revealing a key gap in speaker-aware dialogue understanding. M3-SLU offers as a challenging benchmark to advance research in speaker-aware multimodal understanding.
Anthology ID:
2026.lrec-1.451
Volume:
Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:
LREC
SIG:
Publisher:
ELRA Language Resource Association
Note:
Pages:
5722–5736
Language:
External URL:
https://lrec.elra.info/lrec2026-main-451
DOI:
10.63317/5giy6mqijruy
Bibkey:
Cite (ACL):
Yejin Kwon, Taewoo Kang, Hyunsoo Yoon, and Chang Ouk Kim. 2026. M3-SLU: Evaluating Speaker-Attributed Reasoning in Multimodal Large Language Models. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 5722–5736, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):
M3-SLU: Evaluating Speaker-Attributed Reasoning in Multimodal Large Language Models (Kwon et al., LREC 2026)
Copy Citation: