Task Complexity Matters: An Empirical Study of Reasoning in LLMs for Sentiment Analysis
任务复杂性至关重要:对LLM在情感分析中推理能力的实证研究
机构 * School of Computing and Information Systems, Singapore Management University(新加坡管理学院) ; Research and Development, Mastercard(麦star公司)
专题命中 推理与问题求解 :LLM(title_cn);large language model(abstract);language model(abstract);prompting(abstract)
AI总结 研究通过评估7种模型家族在不同粒度的情感分析数据集上的表现,发现推理效果高度依赖任务复杂性,二分类任务性能下降,多类情感识别性能提升,且少量样本学习在多数情况下优于零样本学习。
Comments 12 pages, 1 figure, 3 tables. Accepted at PAKDD 2026
Journal ref In: Wong, R.CW., et al. Advances in Knowledge Discovery and Data Mining. PAKDD 2026. Lecture Notes in Computer Science(), vol 16600. Springer, Singapore