RE-AdaptIR: Improving Information Retrieval through Reverse Engineered Adaptation

TL;DR

This work uses RE-AdaptIR to improve LLM-based IR models using only unlabeled data and demonstrates improved performance in both training domains and in zero-shot domains where the models have seen no queries.

Abstract

Large language models (LLMs) fine-tuned for text-retrieval have demonstrated state-of-the-art results across several information retrieval (IR) benchmarks. However, supervised training for improving these models requires numerous labeled examples, which are generally unavailable or expensive to acquire. In this work, we explore the effectiveness of extending reverse engineered adaptation to the context of information retrieval (RE-AdaptIR). We use RE-AdaptIR to improve LLM-based IR models using only unlabeled data. We demonstrate improved performance both in training domains as well as zero-shot in domains where the models have seen no queries. We analyze performance changes in various fine-tuning scenarios and offer findings of immediate use to practitioners.