FinSentLLM: Multi-LLM and Structured Semantic Signals for Enhanced Financial Sentiment Forecasting
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914039189209088 |
|---|---|
| author | Zhang, Zijian Fu, Rong He, Yangfan Shen, Xinze Wang, Yanlong Du, Xiaojing You, Haochen Shi, Jiazhao Fong, Simon |
| author_facet | Zhang, Zijian Fu, Rong He, Yangfan Shen, Xinze Wang, Yanlong Du, Xiaojing You, Haochen Shi, Jiazhao Fong, Simon |
| contents | 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 and further establish that sentiment signals are robustly linked to long-run equity market dynamics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_12638 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FinSentLLM: Multi-LLM and Structured Semantic Signals for Enhanced Financial Sentiment Forecasting Zhang, Zijian Fu, Rong He, Yangfan Shen, Xinze Wang, Yanlong Du, Xiaojing You, Haochen Shi, Jiazhao Fong, Simon Computational Engineering, Finance, and Science 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 and further establish that sentiment signals are robustly linked to long-run equity market dynamics. |
| title | FinSentLLM: Multi-LLM and Structured Semantic Signals for Enhanced Financial Sentiment Forecasting |
| topic | Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2509.12638 |