3 papers
cs.AI2026
Source-preserving alignment for robust evidence localization in scientific PDFS
Zihao Liu, Wei Yang, Zixiao Dong +4
Scientific information-extraction systems often return a claim with an evidence string, which users must locate in the original PDF. This is challenging because the extracted evide…
cs.CL2026
Adapt Semantics, Not Structure: Few-Instance Schema Calibration for Scientific PDF Extraction
Zixiao Dong, Wei Yang, Zihao Liu +4
A well-designed extraction schema is not necessarily ready for reliable LLM execution. When only limited verified extractions are available, manually tuning hundreds of field defin…
cs.CL2026
From Weak Task Specifications to Scientific Extraction Agents: Optimizing Task Construction
Zixiao Dong, Wei Yang, Zihao Liu +4
Most methods that optimize LLM prompts and agent workflows assume that task-specific output schemas, extraction instructions, and evaluation criteria are predefined. For scientific…