RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback
arxiv(2024)
摘要
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.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要