Reproduce “FinLLM-KG: Knowledge Graph-Enhanced LLMs for Financial Sentiment Analysis in Algorithmic Trading” 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
Giorgos Iacovides, Oliver Hannibal, Wuyang Zhou, Danilo Mandic
FinLLM-KG adds dated company facts to financial-news sentiment scoring at inference time, without changing the language model’s weights. It uses either a company profile or article-retrieved facts alongside the news, and can attribute score shifts to sentences and facts. In a historical simulation, its top-k-facts version returned 329.54%, versus 275.04% for the baseline, before transaction costs, not live-trading gains.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.