Real-Time Generation of Game Video Commentary with Multimodal LLMs: Pause-Aware Decoding Approaches

Anum Afzal, Yuki Saito, Hiroya Takamura, Katsuhito Sudoh, Shinnosuke Takamichi, Graham Neubig, Florian Matthes, Tatsuya Ishigaki


Abstract
Real-time video commentary generation provides textual descriptions of ongoing events in videos. It supports accessibility and engagement in domains such as sports, esports, and livestreaming. Commentary generation involves two essential decisions: what to say and when to say it. While recent prompting-based approaches using multimodal large language models (MLLMs) have shown strong performance in content generation, they largely ignore the timing aspect. We investigate whether in-context prompting alone can support real-time commentary generation that is both semantically relevant and well-timed. We propose two prompting-based decoding strategies: 1) a fixed-interval approach, and 2) a novel dynamic interval-based decoding approach that adjusts the next prediction timing based on the estimated duration of the previous utterance. Both methods enable pause-aware generation without any fine-tuning. Experiments on Japanese and English datasets of racing and fighting games show that the dynamic interval-based decoding can generate commentary more closely aligned with human utterance timing and content using prompting alone. We release a multilingual benchmark dataset, trained models, and implementations to support future research on real-time video commentary generation.
Anthology ID:
2026.lrec-1.722
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:
9188–9201
Language:
External URL:
https://lrec.elra.info/lrec2026-main-722
DOI:
10.63317/5m3djogm95q9
Bibkey:
Cite (ACL):
Anum Afzal, Yuki Saito, Hiroya Takamura, Katsuhito Sudoh, Shinnosuke Takamichi, Graham Neubig, Florian Matthes, and Tatsuya Ishigaki. 2026. Real-Time Generation of Game Video Commentary with Multimodal LLMs: Pause-Aware Decoding Approaches. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 9188–9201, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):
Real-Time Generation of Game Video Commentary with Multimodal LLMs: Pause-Aware Decoding Approaches (Afzal et al., LREC 2026)
Copy Citation: