InstructRAG：通过自合成原理指导检索增强生成
InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales
AI总结：
提出InstructRAG框架，通过自合成原理让语言模型显式学习去噪过程，无需额外监督即可提升检索增强生成的准确性和可验证性，在五个基准上平均相对提升8.3%。
摘要：
检索增强生成（RAG）已展现出提升语言模型（LM）准确性和事实性的巨大潜力。然而，不完美的检索器或含噪声的语料库会向检索内容中引入误导性甚至错误信息，对生成质量构成重大挑战。现有RAG方法通常通过直接预测最终答案来应对这一挑战，而忽略潜在的噪声输入，这导致一个难以解释和验证的隐式去噪过程。另一方面，获取显式去噪监督往往成本高昂，需要大量人力。在本研究中，我们提出InstructRAG，让LM通过自合成原理显式学习去噪过程——首先，我们指导LM解释如何从检索文档中推导出真实答案。然后，这些原理既可作为上下文学习显式去噪的示例，也可作为监督微调数据来训练模型。与标准RAG方法相比，InstructRAG无需额外监督，允许更轻松地验证预测答案，并有效提升生成准确率。实验表明，InstructRAG在免训练和可训练场景中均持续优于现有RAG方法，在五个知识密集型基准上平均比最佳基线方法相对提升8.3%。广泛分析表明，InstructRAG随检索文档数量增加具有良好的扩展性，即使在域外数据集上也持续展现稳健的去噪能力，证明其强大的泛化性。
英文摘要：
Retrieval-augmented generation (RAG) has shown promising potential to enhance the accuracy and factuality of language models (LMs). However, imperfect retrievers or noisy corpora can introduce misleading or even erroneous information to the retrieved contents, posing a significant challenge to the generation quality. Existing RAG methods typically address this challenge by directly predicting final answers despite potentially noisy inputs, resulting in an implicit denoising process that is difficult to interpret and verify. On the other hand, the acquisition of explicit denoising supervision is often costly, involving significant human efforts. In this work, we propose InstructRAG, where LMs explicitly learn the denoising process through self-synthesized rationales -- First, we instruct the LM to explain how the ground-truth answer is derived from retrieved documents. Then, these rationales can be used either as demonstrations for in-context learning of explicit denoising or as supervised fine-tuning data to train the model. Compared to standard RAG approaches, InstructRAG requires no additional supervision, allows for easier verification of the predicted answers, and effectively improves generation accuracy. Experiments show InstructRAG consistently outperforms existing RAG methods in both training-free and trainable scenarios, achieving a relative improvement of 8.3% over the best baseline method on average across five knowledge-intensive benchmarks. Extensive analysis indicates that InstructRAG scales well with increased numbers of retrieved documents and consistently exhibits robust denoising ability even in out-of-domain datasets, demonstrating strong generalizability.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
