SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.00807 · EMNLP · 2023

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

Omar Khattab, Christopher Potts, Jon Saad-Falcon, Salim Roukos, Keshav Santhanam, Avirup Sil, Radu Florian, Martin Franz, Md Sultan

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2303.00807")
get_code_for_paper("2303.00807")
have("2303.00807")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2303.00807.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2303.00807.svg)](https://syntology.ai/paper/2303.00807)

Connect an agent — have() is free.