# Bayesian Network Fusion of Large Language Models for Sentiment Analysis

arXiv: https://arxiv.org/abs/2510.26484 · HTML: https://mlsanity.com/paper/2510.26484/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 52 references that are in the map.
- First posted on arXiv 30 Oct 2025.

## Builds on (most cited first, 21 of 21)

- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Large Language Models: A Survey](https://mlsanity.com/paper/2402.06196/) (2024)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Texts](https://mlsanity.com/paper/1307.5336/) (2013)
- [CLadder: Assessing Causal Reasoning in Language Models](https://mlsanity.com/paper/2312.04350/) (2023)
- [A Tutorial on Learning With Bayesian Networks](https://mlsanity.com/paper/2002.00269/) (2020)
- [Understanding the Performance and Estimating the Cost of LLM Fine-Tuning](https://mlsanity.com/paper/2408.04693/) (2024)
- [LLM-TOPLA: Efficient LLM Ensemble by Maximising Diversity](https://mlsanity.com/paper/2410.03953/) (2024)
- [Fine-tuning and Utilization Methods of Domain-specific LLMs](https://mlsanity.com/paper/2401.02981/) (2024)
- [Survey of different Large Language Model Architectures: Trends, Benchmarks, and Challenges](https://mlsanity.com/paper/2412.03220/) (2024)
- [Beyond Behaviorist Representational Harms: A Plan for Measurement and Mitigation](https://mlsanity.com/paper/2402.01705/) (2024)
- [MatTools: Benchmarking Large Language Models for Materials Science Tools](https://mlsanity.com/paper/2505.10852/) (2025)
- [Temporal Scaling Law for Large Language Models](https://mlsanity.com/paper/2404.17785/) (2024)
- [AlphaZip: Neural Network-Enhanced Lossless Text Compression](https://mlsanity.com/paper/2409.15046/) (2024)
- [Exploring Prompt Engineering: A Systematic Review with SWOT Analysis](https://mlsanity.com/paper/2410.12843/) (2024)
- [Model Hubs and Beyond: Analyzing Model Popularity, Performance, and Documentation](https://mlsanity.com/paper/2503.15222/) (2025)
- [A Framework for Empowering Reinforcement Learning Agents with Causal Analysis: Enhancing Automated Cryptocurrency Trading](https://mlsanity.com/paper/2310.09462/) (2023)
- [Multimodal Stock Price Prediction](https://mlsanity.com/paper/2502.05186/) (2025)

## Abstract (arXiv)

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.