Towards General Text Embeddings with Multi-stage Contrastive Learning
This provides a more efficient and broadly applicable text embedding solution for NLP and code-related tasks, though it is incremental in its approach.
The authors tackled the problem of creating a general-purpose text embedding model by using multi-stage contrastive learning on diverse datasets, resulting in GTE, a 110M-parameter model that outperforms OpenAI's API and larger models on benchmarks, including code retrieval without language-specific fine-tuning.
We present GTE, a general-purpose text embedding model trained with multi-stage contrastive learning. In line with recent advancements in unifying various NLP tasks into a single format, we train a unified text embedding model by employing contrastive learning over a diverse mixture of datasets from multiple sources. By significantly increasing the number of training data during both unsupervised pre-training and supervised fine-tuning stages, we achieve substantial performance gains over existing embedding models. Notably, even with a relatively modest parameter count of 110M, GTE$_\text{base}$ outperforms the black-box embedding API provided by OpenAI and even surpasses 10x larger text embedding models on the massive text embedding benchmark. Furthermore, without additional fine-tuning on each programming language individually, our model outperforms previous best code retrievers of similar size by treating code as text. In summary, our model achieves impressive results by effectively harnessing multi-stage contrastive learning, offering a powerful and efficient text embedding model with broad applicability across various NLP and code-related tasks.