Reproduce “FinReflectKG - EvalBench: Benchmarking Financial KG with Multi-Dimensional Evaluation” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Fabrizio Dimino, Abhinav Arun, Bhaskarjit Sarmah, Stefano Pasquali

FinReflectKG-EvalBench evaluates financial knowledge graph extraction from fiscal-year-2024 SEC 10-K filings of S&P 100 companies using four dimensions: faithfulness, precision, relevance, and comprehensiveness. Its Qwen3-32B judge uses source-bound instructions and bias controls. Reflection scores 72.01 on comprehensiveness, while single-pass leads on faithfulness; these results compare three modes only in this dataset and judging setup.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.