FinLLM-KG: Knowledge Graph-Enhanced LLMs for Financial Sentiment Analysis in Algorithmic Trading

A new arXiv paper (2610.36083v1) introduces FinLLM-KG, a model-agnostic framework that pairs causal large language models with a financial knowledge graph to inject temporally grounded, company-level knowledge from SEC 10-K filings at inference time without updating model weights. FinLLM-KG supplies context either as a natural-language company profile or as a small set of relevance-ranked factual triples, letting sentiment predictions account for firm-level information rather than a single article at almost zero computational cost, and attributes each article-level sentiment score to individual sentences and retrieved knowledge-graph facts for inspectable, human-in-the-loop review. The paper's simulations report that FinLLM-KG consistently improves portfolio performance over the state-of-the-art baseline.

arXiv:2610.36083v1 Announce Type: new Abstract: Recent advances in Generative AI have substantially improved financial sentiment analysis through post-trained financial large language models LLMs . However, existing approaches remain confined to predicting the sentiment of each article in isolation and operate as black boxes, which limits contextual understanding and hinders deployment in high-stakes financial decision-making. To this end, we introduce FinLLM-KG, a model-agnostic framework that combines causal LLMs with a financial knowledge graph, in order to inject temporally grounded, company-level knowledge from SEC 10-K filings at inference time, without updating model weights. Within FinLLM-KG, context is supplied either as a natural-language company profile or as a small set of relevance-ranked factual triples. This enables sentiment predictions to account for broader firm-level information rather than the article alone, at almost zero computational cost and for any causal LLM. In addition, attributing each article-level sentiment score to individual sentences and to the retrieved knowledge-graph facts makes the evidence behind the prediction inspectable, thereby enhancing explainability and supporting human-in-the-loop review. Simulations demonstrate that FinLLM-KG consistently improves portfolio performance over the state-of-the-art baseline.