Reinforced Information Retrieval

TL;DR

Reinforced-IR introduces a joint retriever-generator framework with a self-boosting mechanism to improve cross-domain information retrieval, especially in specialized domains, by iterative learning from feedback.

Contribution

The paper proposes Reinforced-IR, a novel method that jointly trains a retriever and generator with a self-boosting framework for enhanced cross-domain retrieval performance.

Findings

Reinforced-IR outperforms existing domain adaptation methods significantly.

The self-boosting framework improves retrieval accuracy in specialized domains.

Iterative training enhances the end-to-end retrieval quality.

Abstract

While retrieval techniques are widely used in practice, they still face significant challenges in cross-domain scenarios. Recently, generation-augmented methods have emerged as a promising solution to this problem. These methods enhance raw queries by incorporating additional information from an LLM-based generator, facilitating more direct retrieval of relevant documents. However, existing methods struggle with highly specialized situations that require extensive domain expertise. To address this problem, we present \textbf{Reinforced-IR}, a novel approach that jointly adapts a pre-trained retriever and generator for precise cross-domain retrieval. A key innovation of Reinforced-IR is its \textbf{Self-Boosting} framework, which enables retriever and generator to learn from each other's feedback. Specifically, the generator is reinforced to generate query augmentations that enhance the retriever's performance, while the retriever is trained to better discriminate the relevant documents identified by the generator. This iterative process allows the end-to-end retrieval performance to be progressively optimized using an unlabeled corpus from the target domain. In our experiment, Reinforced-IR outperforms existing domain adaptation methods by a large margin, leading to substantial improvements in retrieval quality across a wide range of application scenarios.