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.

翻译：针对文本检索进行微调的大语言模型（LLM）已在多项信息检索（IR）基准测试中展现出最先进的性能。然而，用于改进这些模型的监督训练需要大量标注样本，而这些样本通常难以获取或获取成本高昂。在本研究中，我们探讨了将逆向工程自适应方法扩展至信息检索领域（RE-AdaptIR）的有效性。我们利用RE-AdaptIR，仅使用未标注数据即可改进基于LLM的信息检索模型。我们证明了该方法不仅在训练领域内能提升性能，在模型未见过任何查询的领域也能实现零样本性能改进。我们分析了不同微调场景下的性能变化，并提供了可供从业者直接应用的发现。