Bayesian Network Fusion of Large Language Models for Sentiment Analysis

TL;DR

This paper introduces a Bayesian network-based fusion framework that combines multiple large language models for sentiment analysis, achieving more accurate and interpretable results across diverse financial datasets.

Contribution

The paper presents a novel probabilistic fusion method, BNLF, that improves sentiment analysis accuracy by integrating predictions from multiple LLMs within a Bayesian network.

Findings

BNLF achieves about 6% higher accuracy than individual LLMs.

Demonstrates robustness across different financial datasets.

Provides interpretable sentiment predictions through probabilistic modeling.

Abstract

Large language models (LLMs) continue to advance, with an increasing number of domain-specific variants tailored for specialised tasks. However, these models often lack transparency and explainability, can be costly to fine-tune, require substantial prompt engineering, yield inconsistent results across domains, and impose significant adverse environmental impact due to their high computational demands. To address these challenges, we propose the Bayesian network LLM fusion (BNLF) framework, which integrates predictions from three LLMs, including FinBERT, RoBERTa, and BERTweet, through a probabilistic mechanism for sentiment analysis. BNLF performs late fusion by modelling the sentiment predictions from multiple LLMs as probabilistic nodes within a Bayesian network. Evaluated across three human-annotated financial corpora with distinct linguistic and contextual characteristics, BNLF demonstrates consistent gains of about six percent in accuracy over the baseline LLMs, underscoring its robustness to dataset variability and the effectiveness of probabilistic fusion for interpretable sentiment classification.