无需预训练，用对比学习让大模型变高效检索器
LLM2IR: simple unsupervised contrastive learning makes long-context LLM great retriever
- 用无监督对比学习将任意解码器型大模型转为检索模型
- 在多个基准上表现优于现有方法，长上下文模型更擅长检索
- 适合想快速构建检索系统的开发者，尤其关注上下文长度的优化
当前密集检索模型通常依赖昂贵的大规模预训练。本文提出 LLM2IR，一种高效的无监督对比学习框架，可将任意解码器型大语言模型转化为信息检索模型。尽管方法简单，但在多个检索基准（包括 LoCo、LongEmbed 和 BEIR）上验证了其有效性。我们发现，在同一模型家族中，上下文长度越长的模型，检索能力越强。该工作不仅为基于先进大模型构建检索系统提供了有效途径，还揭示了检索能力与模型上下文长度之间的关系，对设计更优检索器具有指导意义。
原文摘要 · Abstract (English)
Modern dense information retrieval (IR) models usually rely on costly large-scale pretraining. In this paper, we introduce LLM2IR, an efficient unsupervised contrastive learning framework to convert any decoder-only large language model (LLM) to an information retrieval model. Despite its simplicity, the effectiveness is proven among different LLMs on multiple IR benchmarks including LoCo, LongEmbed and BEIR. We also find that models with a longer context length tend to have a stronger IR capacity by comparing task performances of models in the same model family. Our work not only provides an effective way to build IR models on the state-of-the-art LLMs, but also shed light on the relationship between information retrieval ability and model context length, which helps the design of better information retrievers.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。