2023/10/13 by Carlos Domínguez, Jon Ander Campos, Dominguez, Carlos +5
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2310.09350
openalex publication_date 2023/10/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Neural information retrieval requires costly annotated data for each target domain to be competitive. Synthetic annotation by query generation using Large Language Models or rule-based string manipulation has been proposed as an alternative, but their relative merits have not been analysed. In this paper, we compare both methods head-to-head using the same neural IR architecture. We focus on the BEIR benchmark, which includes test datasets from several domains with no training data, and explore two scenarios: zero-shot, where the supervised system is trained in a large out-of-domain dataset (MS-MARCO); and unsupervised domain adaptation, where, in addition to MS-MARCO, the system is fine-tuned in synthetic data from the target domain. Our results indicate that Large Language Models outperform rule-based methods in all scenarios by a large margin, and, more importantly, that unsupervised domain adaptation is effective compared to applying a supervised IR system in a zero-shot fashion. In addition we explore several sizes of open Large Language Models to generate synthetic data and find that a medium-sized model suffices. Code and models are publicly available for reproducibility.