用问答中间步骤提升大模型摘要能力，无需微调
QA-prompting: Improving Summarization with Large Language Models using Question-Answering
- 先提问再回答，用问答增强上下文信息
- 在多个数据集上提升29%的ROUGE得分
- 适合需要高效摘要的场景，无需额外训练
大语言模型在自然语言处理中通过提示和上下文学习实现了高质量文本生成，但在长文本摘要任务中常因位置偏差导致关键信息提取不佳。现有改进方法如微调、流水线或复杂技术存在各自挑战。为此，我们提出QA-prompting——一种简单提示方法，通过在生成摘要前引入问答中间步骤，提取关键信息并丰富上下文，以缓解位置偏差问题。该方法在单次模型调用中完成，无需微调或流水线。在涵盖不同领域的多个数据集上，使用十种先进预训练模型的实验表明，QA-prompting优于基线和其他先进方法，最高实现29%的ROUGE分数提升，提供了一种高效可扩展的摘要解决方案，并强调领域特定问题选择对性能的关键作用。
原文摘要 · Abstract (English)
Language Models (LMs) have revolutionized natural language processing, enabling high-quality text generation through prompting and in-context learning. However, models often struggle with long-context summarization due to positional biases, leading to suboptimal extraction of critical information. There are techniques to improve this with fine-tuning, pipelining, or using complex techniques, which have their own challenges. To solve these challenges, we propose QA-prompting - a simple prompting method for summarization that utilizes question-answering as an intermediate step prior to summary generation. Our method extracts key information and enriches the context of text to mitigate positional biases and improve summarization in a single LM call per task without requiring fine-tuning or pipelining. Experiments on multiple datasets belonging to different domains using ten state-of-the-art pre-trained models demonstrate that QA-prompting outperforms baseline and other state-of-the-art methods, achieving up to 29% improvement in ROUGE scores. This provides an effective and scalable solution for summarization and highlights the importance of domain-specific question selection for optimal performance.
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。