PRCA: Fitting Black-Box Large Language Models for Retrieval Question Answering via Pluggable Reward-Driven Contextual Adapter
https://papers.cool/arxiv/2310.18347
Authors: Haoyan Yang ; Zhitao Li ; Yong Zhang ; Jianzong Wang ; Ning Cheng ; Ming Li ; Jing Xiao
Summary: The Retrieval Question Answering (ReQA) task employs the retrieval-augmented framework, composed of a retriever and generator. The generator formulates the answer based on the documents retrieved by the retriever. Incorporating Large Language Models (LLMs) as generators is beneficial due to their advanced QA capabilities, but they are typically too large to be fine-tuned with budget constraints while some of them are only accessible via APIs. To tackle this issue and further improve ReQA performance, we propose a trainable Pluggable Reward-Driven Contextual Adapter (PRCA), keeping the generator as a black box. Positioned between the retriever and generator in a Pluggable manner, PRCA refines the retrieved information by operating in a token-autoregressive strategy via maximizing rewards of the reinforcement learning phase. Our experiments validate PRCA's effectiveness in enhancing ReQA performance on three datasets by up to 20% improvement to fit black-box LLMs into existing frameworks, demonstrating its considerable potential in the LLMs era.
A: 这篇论文试图解决的问题是如何在有限的计算预算下,有效地整合大型语言模型(LLMs)作为生成器,以提高检索式问答(ReQA)任务的性能。具体来说,论文面临的挑战包括:
为了解决这些问题,论文提出了一个可训练的、可插拔的奖励驱动上下文适配器(Pluggable Reward-Driven Contextual Adapter, PRCA),它能够在不改变检索器和生成器的情况下,通过最大化强化学习阶段的奖励来精炼检索到的信息,从而提高ReQA任务的性能。
A: 相关研究主要集中在以下几个方面:
这些相关研究为本文提出的PRCA方法提供了背景和基础,特别是在如何有效地利用LLMs以及如何改进检索增强框架以提高问答任务性能方面。