优化提示词与微调，让摘要更贴合问答社区中的不同观点。
UMB@PerAnsSumm 2025: Enhancing Perspective-Aware Summarization with Prompt Optimization and Supervised Fine-Tuning
- 用三种Transformer模型集成识别观点片段，F1达82.91%
- 设计带关键词和步骤引导的提示链，提升摘要结构化程度
- 结合提示优化与微调，在相关性和事实性上显著提升
我们针对PerAnsSumm共享任务提出方法，涵盖社区问答（CQA）线程中的观点片段识别与观点感知摘要生成。在片段识别上，采用三种Transformer模型的集成学习，通过平均融合各模型优势，在测试集上达到82.91%的F1分数。在摘要生成方面，设计了一套包含关键词与分步引导的思维链（CoT）提示策略，将信息组织过程分解为可管理步骤。为进一步提升摘要质量，使用DSPy框架进行提示优化，并在Llama-3上进行领域数据的监督微调（SFT）。在验证集和测试集上的实验表明，结构化提示配合关键词和引导可提高摘要与参考文本的一致性；而提示优化与微调联合使用，在相关性与事实性评估指标上均取得显著提升。
原文摘要 · Abstract (English)
We present our approach to the PerAnsSumm Shared Task, which involves perspective span identification and perspective-aware summarization in community question-answering (CQA) threads. For span identification, we adopt ensemble learning that integrates three transformer models through averaging to exploit individual model strengths, achieving an 82.91% F1-score on test data. For summarization, we design a suite of Chain-of-Thought (CoT) prompting strategies that incorporate keyphrases and guide information to structure summary generation into manageable steps. To further enhance summary quality, we apply prompt optimization using the DSPy framework and supervised fine-tuning (SFT) on Llama-3 to adapt the model to domain-specific data. Experimental results on validation and test sets show that structured prompts with keyphrases and guidance improve summaries aligned with references, while the combination of prompt optimization and fine-tuning together yields significant improvement in both relevance and factuality evaluation metrics.
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。