RE-AdaptIR:通过逆向工程适配改进信息检索
RE-AdaptIR: Improving Information Retrieval through Reverse Engineered Adaptation
AI总结:
针对信息检索模型监督训练需大量标注数据的问题,提出RE-AdaptIR方法,仅用无标注数据改进基于大语言模型的检索模型,在训练域和零样本域均实现性能提升,相关发现可供从业者参考。
摘要:
针对文本检索微调的大语言模型(LLM)已在多个信息检索(IR)基准测试中展现出最优性能。然而,为改进这些模型进行的监督训练需要大量标注样本,这类样本通常难以获取且标注成本高昂。本研究探索了将逆向工程适配拓展至信息检索场景(即RE-AdaptIR)的有效性。我们使用RE-AdaptIR仅依靠无标注数据改进基于LLM的IR模型,在训练领域内以及模型从未接触过查询的零样本领域中均实现了性能提升。我们分析了多种微调场景下的性能变化,所得发现可供从业者直接参考使用。
英文摘要:
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.
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。