FinSentLLM: Multi-LLM and Structured Semantic Signals for Enhanced Financial Sentiment Forecasting
Year: 2026
Type: conference-paper
Abstract: Financial sentiment analysis (FSA) has attracted significant attention, and recent studies increasingly explore large language models (LLMs) for this field. Yet most work evaluates only classification metrics, leaving unclear whether sentiment signals align with market behavior. We propose FinSentLLM, a lightweight multi-LLM framework that integrates an expert panel of sentiment forecasting LLMs, and structured semantic financial signals via a compact meta-classifier. This design captures expert complementarity, semantic reasoning signal, and agreement/divergence patterns without costly retraining, yielding consistent 3–6% gains over strong baselines in accuracy and F1-score on the Financial PhraseBank dataset. In addition, we also provide econometric evidence that financial sentiment and stock markets exhibit statistically significant long-run comovement, applying Dynamic Conditional Correlation GARCH (DCC–GARCH) and the Johansen cointegration test to daily sentiment scores computed from the FNSPID dataset and major stock indices. Together, these results demonstrate that FinSentLLM delivers superior forecasting accuracy for financial sentiment, while providing econometric evidence of statistically significant correlation and long-run comovement between sentiment signals and equity markets.
Authors: Zijian Zhang, Rong Fu, Yangfan He, Xinze Shen, Yanlong Wang, Xiaojing Du, Haochen You, Keyan Jin, Jiazhao Shi, Simon Fong
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4415316358