用推理生成+列表偏好优化，提升四元组情感预测准确率
Listwise Preference Optimization with Element-wise Confusions for Aspect Sentiment Quad Prediction
- 通过自然语言理由引导模型进行元素间关系推理
- 在四个数据集上四元组准确率显著提升，解释一致性更强
- 适合需要可解释性的情感分析任务
方面情感四元组预测（ASQP）需同时识别四个核心情感元素：方面词（a）、方面类别（c）、观点词（o）和情感极性（s），具有很强的结构复杂性。以往基于标记的方法难以建模元素间的复杂关系，在标准监督微调下对高阶元素（如c和s）预测性能急剧下降。为此，我们采用基于推理的生成方法，在统一模板中以元素前缀输出四元组及自然语言解释，促进显式关系推理与可解释性。为进一步增强元素对齐，提出一种列表偏好优化框架，通过语法和语义相似性生成元素混淆候选，训练模型在列表级目标下更偏好真实答案而非近似竞争项。在四个基准数据集上的实验表明，该框架有效提升了四元组预测准确率与解释一致性。
原文摘要 · Abstract (English)
Aspect sentiment quad prediction (ASQP) is inherently challenging to predict a structured quadruple with four core sentiment elements, including aspect term (a), aspect category (c), opinion term (o), and sentiment polarity (s). Prior methods relying on marker-based prediction struggle with modeling the intricate relationships among elements and experience sharp performance declines when predicting higher-order elements (e.g., c and s) under standard supervised fine-tuning. To address these limitations, we employ reasoning-based generation to output both the quadruple and a natural language rationale under element prefixes within a unified template, encouraging explicit relational reasoning and interpretability. To further enhance element-wise alignment, we introduce a listwise preference optimization framework for improving structural validity and relational coherence. Specifically, we generate element-wise confusable candidates via syntactic and semantic proximity, then train the model with listwise objectives to prefer the gold candidates over closely competing alternatives. Extensive experiments on four benchmark datasets demonstrate that our framework effectively improves quadruple prediction accuracy and explanation consistency.
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。