arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.14739cs.CL
收藏

面向上下文学习的迭代检索学习方法

Learning to Retrieve Iteratively for In-Context Learning

Johns Hopkins University(约翰斯·霍普金斯大学);Microsoft(微软);Google(谷歌)

Yunmo Chen, Tongfei Chen, Harsh Jhamtani, Patrick Xia, Richard Shin, Jason Eisner, Benjamin Van Durme

AI总结:

本研究提出迭代检索框架,通过强化学习训练带状态的迭代检索器来选择ICL示例,仅新增4M参数就在多个语义解析数据集上超越现有方法,且能泛化到不同推理LLM。

摘要:

我们提出了迭代检索(iterative retrieval)这一新型框架,该框架通过策略优化使检索器能够进行迭代决策。寻找最优的检索项组合是一个组合优化问题,通常被认为是NP难问题。该方法为这类问题提供了一种可学习的近似解,能够在给定的大语言模型(LLM)系列下满足特定的任务需求。我们提出了一种基于强化学习的训练流程,融入了来自LLM的反馈。我们构建了一个用于组合上下文学习(ICL)示例的迭代检索器,并将其应用于多种需要输出合成程序的语义解析任务。仅通过添加400万个用于状态编码的额外参数,我们就将现成的密集检索器转换为有状态的迭代检索器,在CalFlow、TreeDST和MTOP等语义解析数据集的ICL示例选择任务上,性能优于先前的方法。此外,经过训练的迭代检索器能够泛化到训练时所用LLM之外的不同推理LLM上。

英文摘要:

We introduce iterative retrieval, a novel framework that empowers retrievers to make iterative decisions through policy optimization. Finding an optimal portfolio of retrieved items is a combinatorial optimization problem, generally considered NP-hard. This approach provides a learned approximation to such a solution, meeting specific task requirements under a given family of large language models (LLMs). We propose a training procedure based on reinforcement learning, incorporating feedback from LLMs. We instantiate an iterative retriever for composing in-context learning (ICL) exemplars and apply it to various semantic parsing tasks that demand synthesized programs as outputs. By adding only 4M additional parameters for state encoding, we convert an off-the-shelf dense retriever into a stateful iterative retriever, outperforming previous methods in selecting ICL exemplars on semantic parsing datasets such as CalFlow, TreeDST, and MTOP. Additionally, the trained iterative retriever generalizes across different inference LLMs beyond the one used during training.

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。

↑