用概率模型融合多个大模型，提升情感分析准确率与可解释性
Bayesian Network Fusion of Large Language Models for Sentiment Analysis
- 通过贝叶斯网络对三个大模型的预测结果进行概率融合
- 在金融语料上比单个模型平均高6%准确率
- 适合需要可解释性与稳定性能的金融情感分析场景
大型语言模型（LLMs）持续发展，涌现出大量针对特定任务的领域变体。然而，这些模型往往缺乏透明性与可解释性，微调成本高，需大量提示工程，跨领域表现不一致，且因计算需求大带来显著环境负担。为此，我们提出贝叶斯网络大模型融合（BNLF）框架，通过概率机制集成FinBERT、RoBERTa与BERTweet三个LLM的预测结果，用于情感分析。BNLF采用晚期融合策略，将多个LLM的预测视为贝叶斯网络中的概率节点。在三个具有不同语言与上下文特征的人工标注金融语料上评估，BNLF相比基线模型在准确率上实现约6%的稳定提升，表明其对数据集差异具有鲁棒性，验证了概率融合在可解释情感分类中的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。