UDAPDR: Unsupervised Domain Adaptation via LLM Prompting and Distillation of Rerankers

Autor:	Saad-Falcon, Jon, Khattab, Omar, Santhanam, Keshav, Florian, Radu, Franz, Martin, Roukos, Salim, Sil, Avirup, Sultan, Md Arafat, Potts, Christopher
Rok vydání:	2023
Předmět:	Computer Science - Information Retrieval Computer Science - Computation and Language
Druh dokumentu:	Working Paper
Popis:	Many information retrieval tasks require large labeled datasets for fine-tuning. However, such datasets are often unavailable, and their utility for real-world applications can diminish quickly due to domain shifts. To address this challenge, we develop and motivate a method for using large language models (LLMs) to generate large numbers of synthetic queries cheaply. The method begins by generating a small number of synthetic queries using an expensive LLM. After that, a much less expensive one is used to create large numbers of synthetic queries, which are used to fine-tune a family of reranker models. These rerankers are then distilled into a single efficient retriever for use in the target domain. We show that this technique boosts zero-shot accuracy in long-tail domains and achieves substantially lower latency than standard reranking methods. Comment: Long Paper at Empirical Methods in Natural Language Processing (EMNLP) 2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2303.00807 Zobrazit plný text záznamu View this record from Arxiv