SOURCE-LINKED INTELLIGENCE

Does task decomposition improve automatic NLG evaluation?

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

The LLM-as-a-judge (LLMaJ) framework has emerged as a promising solution for cheap, reproducible, reference-free Natural Language Generation (NLG) evaluation. Prior work seeks to improve LLMaJ by decomposing evaluation tasks into simpler sub-tasks. In this work, we systematically compare LLMaJ methods with and without decomposition on multiple NLG datasets. We find no evidence that LLMaJ with task decomposition leads to performance gains over a fair baseline that does not use decomposition. Instead, we find that previously reported performance gains in decomposition-based LLMaJ stem from using

Read original source ↗ Open in workspace

recordType

paper

region

Global