用推理增强大模型，实现多语言、细粒度的情感分析
Large-Scale Aspect-Based Sentiment Analysis with Reasoning-Infused LLMs
- 引入链式思维训练与新型预训练技术，提升模型推理能力
- 在17个数据集上构建20倍于SemEval14的大规模基准，准确率领先现有模型10个百分点
- 支持五类情感分类与多语言部署，适合企业级文本情绪分析场景
我们提出Arctic-ABSA，一套面向真实商业场景的细粒度情感分析模型。模型基于大规模公开数据与精心生成的合成数据训练，构建的数据集规模达SemEval14的20倍。将情感类别从标准的三类扩展至五类（新增混合与未知类），并联合预测整体文本情感，支持多语言。通过在链式思维（CoT）示例上微调，并引入针对编码器模型的新型推理预训练方法，显著提升下游微调效果与泛化能力。395M参数编码器与8B参数解码器在准确性上比GPT-4o和Claude 3.5 Sonnet高出最多10个百分点，在SemEval14上刷新纪录。单个跨语言模型在六种语言中保持87%-91%准确率，且不损害英语表现。我们还发布了ABSA-mix，整合了17个公共数据集，覆盖92个领域。
原文摘要 · Abstract (English)
We introduce Arctic-ABSA, a collection of powerful models for real-life aspect-based sentiment analysis (ABSA). Our models are tailored to commercial needs, trained on a large corpus of public data alongside carefully generated synthetic data, resulting in a dataset 20 times larger than SemEval14. We extend typical ABSA models by expanding the number of sentiment classes from the standard three (positive, negative, neutral) to five, adding mixed and unknown classes, while also jointly predicting overall text sentiment and supporting multiple languages. We experiment with reasoning injection by fine-tuning on Chain-of-Thought (CoT) examples and introduce a novel reasoning pretraining technique for encoder-only models that significantly improves downstream fine-tuning and generalization. Our 395M-parameter encoder and 8B-parameter decoder achieve up to 10 percentage points higher accuracy than GPT-4o and Claude 3.5 Sonnet, while setting new state-of-the-art results on the SemEval14 benchmark. A single multilingual model maintains 87-91% accuracy across six languages without degrading English performance. We release ABSA-mix, a large-scale benchmark aggregating 17 public ABSA datasets across 92 domains.
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。