As more than 70$\%$ of reviews in the existing opinion summary data set are positive, current opinion summarization approaches are reluctant to generate negative summaries given the input of negative texts. To address such sentiment bias, a direct approach without the over-reliance on a specific framework is to generate additional data based on large language models to balance the emotional distribution of the dataset. However, data augmentation based on large language models faces two disadvantages: 1) the potential issues or toxicity in the augmented data; 2) the expensive costs. Therefore, in this paper, we propose a novel data augmentation framework based on both large and small language models for debiasing opinion summarization. In specific, a small size of synthesized negative reviews is obtained by rewriting the positive text via a large language model. Then, a disentangle reconstruction model is trained based on the generated data. After training, a large amount of synthetic data can be obtained by decoding the new representation obtained from the combination of different sample representations and filtering based on confusion degree and sentiment classification. Experiments have proved that our framework can effectively alleviate emotional bias same as using only large models, but more economically.

翻译：现有观点总结数据集中超过70%的评论为正面评价，导致当前观点总结方法在输入负面文本时倾向于回避生成负面摘要。为消除此类情感偏差，一种不依赖特定框架的直接方法是通过大型语言模型生成额外数据以平衡数据集的情感分布。然而，基于大型语言模型的数据增强面临两大缺陷：1）增强数据可能存在潜在问题或毒性；2）成本高昂。为此，本文提出一种基于大、小语言模型的新型数据增强框架，用于消除观点总结中的情感偏差。具体而言，首先通过大型语言模型对正面文本进行改写，获取少量合成负面评论；随后基于生成数据训练解耦重建模型；训练完成后，通过解码不同样本表示组合得到的新表示，并基于困惑度与情感分类进行过滤，即可获取大量合成数据。实验证明，本框架在仅使用大型模型同等消除情感偏差的同时，更具经济性。