PolicyBench is the first large-scale US-China policy comprehension benchmark for LLMs with 21K cases, paired with PolicyMoE that performs best on application and structured reasoning tasks.
We identified and removed duplicates by checking for high sim- ilarity in document titles and textual content
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PolicyLLM: Towards Excellent Comprehension of Public Policy for Large Language Models
PolicyBench is the first large-scale US-China policy comprehension benchmark for LLMs with 21K cases, paired with PolicyMoE that performs best on application and structured reasoning tasks.