A Retrieval-Augmented Multiagent System for Financial Sentiment Analysis
- 14 April 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Systems
- Vol. 40 (2) , 15-22
Abstract
Financial sentiment analysis (FSA) has seen substantial advancements with the use of large language models (LLMs). Previous research highlighted the effectiveness of retrieval-augmented generation (RAG) and multiagent LLMs for FSA as these approaches alleviate the problems of hallucination, a lack of factual knowledge, and limited complex problem-solving capability. Despite this, the interplay and potential synergies between these two methods remain largely unexplored. This study presents a notable leap forward by introducing a retrieval-augmented multiagent system (RAMAS) to enhance LLM-based FSA performance. An RAMAS is specifically designed to deepen understanding of the critical factors that are inherent in FSA and mimic human-like consensus-making processes by adaptively learning from semantically similar few-shot samples and engaging in conversations among the generator, discriminator, and arbitrator agents. Our evaluation of RAMASs demonstrates improved accuracy and F1-score across multiple established FSA benchmark datasets.Keywords
This publication has 12 references indexed in Scilit:
- An Evaluation of Reasoning Capabilities of Large Language Models in Financial Sentiment Analysis2024
- Financial Sentiment Analysis: Techniques and ApplicationsACM Computing Surveys, 2024
- FinSenticNet: A Concept-Level Lexicon for Financial Sentiment Analysis2023
- Discovering the Cognition behind Language: Financial Metaphor Analysis with MetaPro2023
- Enhancing Financial Sentiment Analysis via Retrieval Augmented Large Language Models2023
- Transforming sentiment analysis in the financial domain with ChatGPTMachine Learning with Applications, 2023
- FinBERT: A Large Language Model for Extracting Information from Financial Text*Contemporary Accounting Research, 2023
- Sentiment analysis of financial news articles using performance indicatorsKnowledge and Information Systems, 2017
- Good debt or bad debt: Detecting semantic orientations in economic textsJournal of the Association for Information Science and Technology, 2013
- When Is a Liability Not a Liability? Textual Analysis, Dictionaries, and 10‐KsThe Journal of Finance, 2011