GameCommBench: A Unified Benchmark and Type-Aware Evaluation for AI-Generated Game Commentary
We introduce GameCommBench, a unified benchmark spanning board games, sports, and esports, with commentary aligned to heterogeneous game contexts and annotated by commentary type.
ProofPaper ↗
Key points
- Game commentary is an open-ended generation task requiring multimodal perception, strategic reasoning, and contextual knowledge.
- Existing AI-Generated Game Commentary (AI-GGC) studies remain fragmented across games, modalities, and evaluation protocols, while overlap-based or holistic evaluators fail to capture the functional heterogeneity of commentary.
- We further propose Type-Aware Commentary Evaluation (TACE), a structured framework for evaluating different types of commentary.
- Together, GameCommBench and TACE provide a diagnostic foundation for comparable and interpretable AI-GGC evaluation.
Sources (1)
- [1]GameCommBench: A Unified Benchmark and Type-Aware Evaluation for AI-Generated Game CommentaryarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 02:55 AM
We introduce GameCommBench, a unified benchmark spanning board games, sports, and esports, with commentary aligned to heterogeneous game contexts and annotated by commentary type.
Game commentary is an open-ended generation task requiring multimodal perception, strategic reasoning, and contextual knowledge.
Extractive summary: sentences quoted from the sources.