Large language models (LLMs) demonstrate exceptional performance in numerous tasks but still heavily rely on knowledge stored in their parameters. Moreover, updating this knowledge incurs high training costs. Retrieval-augmented generation (RAG) methods address this issue by integrating external knowledge. The model can answer questions it couldn't previously by retrieving knowledge relevant to the query. This approach improves performance in certain scenarios for specific tasks. However, if irrelevant texts are retrieved, it may impair model performance. In this paper, we propose Retrieval Augmented Iterative Self-Feedback (RA-ISF), a framework that iteratively decomposes tasks and processes them in three submodules to enhance the model's problem-solving capabilities. Experiments show that our method outperforms existing benchmarks, performing well on models like GPT3.5, Llama2, significantly enhancing factual reasoning capabilities and reducing hallucinations.

翻译：大语言模型（LLMs）在众多任务中展现出卓越性能，但仍严重依赖其参数中存储的知识。此外，更新这些知识需要高昂的训练成本。检索增强生成（RAG）方法通过整合外部知识来应对这一问题。模型可通过检索与查询相关的知识来回答其原本无法解答的问题。这种方法在特定任务的部分场景中提升了性能。然而，若检索到无关文本，则可能损害模型性能。本文提出检索增强迭代自反馈（RA-ISF）框架，该框架通过迭代分解任务并在三个子模块中处理，以增强模型的问题求解能力。实验表明，我们的方法优于现有基准，在GPT3.5、Llama2等模型上表现优异，显著提升了事实推理能力并减少了幻觉。