Efficient fine-tuning methodology of text embedding models for information retrieval: contrastive learning penalty (clp)
This work addresses the problem of enhancing retrieval accuracy for information retrieval systems, particularly in applications like RAG, but appears incremental as it builds on existing fine-tuning and contrastive learning approaches.
The study tackled improving information retrieval performance of pre-trained text embedding models by proposing an efficient fine-tuning methodology, including a novel Contrastive Learning Penalty function, and achieved significant performance improvements over existing methods in document retrieval tasks.
Text embedding models play a crucial role in natural language processing, particularly in information retrieval, and their importance is further highlighted with the recent utilization of RAG (Retrieval- Augmented Generation). This study presents an efficient fine-tuning methodology encompassing data selection, loss function, and model architecture to enhance the information retrieval performance of pre-trained text embedding models. In particular, this study proposes a novel Contrastive Learning Penalty function that overcomes the limitations of existing Contrastive Learning. The proposed methodology achieves significant performance improvements over existing methods in document retrieval tasks. This study is expected to contribute to improving the performance of information retrieval systems through fine-tuning of text embedding models. The code for this study can be found at https://github.com/CreaLabs/Enhanced-BGE-M3-with-CLP-and-MoE, and the best-performing model can be found at https://huggingface.co/CreaLabs.