Author

Yangda Peng

h-index 1 View on Semantic Scholar

We have 1 of 4 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Jun 2026

Can LLM-as-a-Judge Reliably Verify Rubrics in Agentic Scenarios?

RuVerBench is introduced, the first benchmark for assessing LaaJ reliability in rubric verification for agentic scenarios, and the impact of key LaaJ strategies, including prompt design, batching, and majority voting, on rubric verification is analyzed.

Yangda Peng, Yunjia Qi, Hao Peng et al. · arXiv.org · 2 citations