finkg-news-9b000efb·1 events·first seen Aliases: FinKG-News
Researchers introduce FinKG-News, a framework that constructs news-centric financial knowledge graphs by extracting events linked to companies, then uses these graphs as grounded evidence for in-context learning to generate credit risk reports. The system is evaluated across three financial dimensions and outperforms baselines by 19-34% on quality metrics while reducing hallucinations. A notable finding is that automated hallucination detection and quality assessment remain unreliable for this domain, requiring expert judgment. Code and resources are publicly released.