CPSE is introduced, a contract-preserving semantic extraction framework that jointly calibrates extraction prompts and field-level semantic descriptions from a few gold annotations that enables low-resource schema execution while preserving the output structure required downstream.
Zi-Xiao Dong, Wei Yang, Zi-Hao Liu et al.· 0 citations
Most methods that optimize LLM prompts and agent workflows assume that task-specific output schemas, extraction instructions, and evaluation criteria are predefined. For scientific extraction agents, however, a short task goal may not fully determine these components, while specifying them manually is costly. We study...
Zi-Xiao Dong, Wei Yang, Zi-Hao Liu et al.· 0 citations
A source-preserving alignment framework that aligns evidence with normalized page text, maps matches back to source-character spans, and renders only their geometry, demonstrating that reliable evidence verification requires robust matching and precise localization within a shared source-preserving alignment representa...
Zi-Hao Liu, Wei Yang, Zi-Xiao Dong et al.· 0 citations
SureRoute is introduced, a chemical verifier-anchored retrosynthesis platform that suppresses Chemical Hallucination and shows that reliable scientific AI requires not only strong generation, but executable verification.
Jieli Zhou, Nai-Wu Chen, Long-Zhang Liu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.