Self-RAG：通过自我反思学习检索、生成和评判
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
AI总结：
提出Self-RAG框架，通过训练模型按需检索并利用反思标记进行自我评判，显著提升了大型语言模型在多种任务上的事实性与生成质量。
摘要：
尽管大型语言模型（LLMs）能力卓越，但仅依赖其内部参数化知识，常会产生包含事实错误的回复。检索增强生成（RAG）作为一种通过检索相关知识来增强LMs的临时方案，减少了此类问题。然而，不分情况地检索并引入固定数量的段落，而不考虑检索是否必要或段落是否相关，会削弱LM的通用性，或导致生成无用的回复。我们提出了一种名为Self-Reflective Retrieval-Augmented Generation（Self-RAG）的新框架，通过检索和自我反思来提升LM的质量和事实性。该框架训练单个任意LM，使其能够按需自适应地检索段落，并使用称为反思标记的特殊标记，对检索到的段落及其自身的生成内容进行生成和反思。生成反思标记使LM在推理阶段可控，从而能根据不同任务需求调整其行为。实验表明，Self-RAG（7B和13B参数）在多种任务上显著优于当前最先进的LLMs和检索增强模型。具体而言，Self-RAG在开放域QA、推理和事实验证任务上优于ChatGPT和检索增强的Llama2-chat，并且在提升长文本生成的事实性和引用准确性方面，相较于这些模型展现出显著优势。
英文摘要：
Despite their remarkable capabilities, large language models (LLMs) often produce responses containing factual inaccuracies due to their sole reliance on the parametric knowledge they encapsulate. Retrieval-Augmented Generation (RAG), an ad hoc approach that augments LMs with retrieval of relevant knowledge, decreases such issues. However, indiscriminately retrieving and incorporating a fixed number of retrieved passages, regardless of whether retrieval is necessary, or passages are relevant, diminishes LM versatility or can lead to unhelpful response generation. We introduce a new framework called Self-Reflective Retrieval-Augmented Generation (Self-RAG) that enhances an LM's quality and factuality through retrieval and self-reflection. Our framework trains a single arbitrary LM that adaptively retrieves passages on-demand, and generates and reflects on retrieved passages and its own generations using special tokens, called reflection tokens. Generating reflection tokens makes the LM controllable during the inference phase, enabling it to tailor its behavior to diverse task requirements. Experiments show that Self-RAG (7B and 13B parameters) significantly outperforms state-of-the-art LLMs and retrieval-augmented models on a diverse set of tasks. Specifically, Self-RAG outperforms ChatGPT and retrieval-augmented Llama2-chat on Open-domain QA, reasoning and fact verification tasks, and it shows significant gains in improving factuality and citation accuracy for long-form generations relative to these models.
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。
