UReason: Benchmarking Reasoning-to-Generation Alignment in Unified Multimodal Models
UReason is introduced, a benchmark for evaluating reasoning-to-generation alignment in this paradigm, consisting of 2,000 human-curated and human-verified instances spanning five reasoning-intensive tasks: Code, Arithmetic, Spatial, Attribute, and Text, and it is found that decontextualized generation consistently outperforms reasoning-guided generation by a large margin.
Cheng Yang, Chufan Shi, Bo Shui et al.
· 5 citations