Improving embedding with contrastive fine-tuning on small datasets with expert-augmented scores

Autor:	Lu, Jun, Li, David, Ding, Bill, Kang, Yu
Rok vydání:	2024
Předmět:	Computer Science - Computation and Language Computer Science - Artificial Intelligence Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	This paper presents an approach to improve text embedding models through contrastive fine-tuning on small datasets augmented with expert scores. It focuses on enhancing semantic textual similarity tasks and addressing text retrieval problems. The proposed method uses soft labels derived from expert-augmented scores to fine-tune embedding models, preserving their versatility and ensuring retrieval capability is improved. The paper evaluates the method using a Q\&A dataset from an online shopping website and eight expert models. Results show improved performance over a benchmark model across multiple metrics on various retrieval tasks from the massive text embedding benchmark (MTEB). The method is cost-effective and practical for real-world applications, especially when labeled data is scarce.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2408.11868 Zobrazit plný text záznamu View this record from Arxiv