While large language models (LLMs) have demonstrated remarkable capabilities across a
range of downstream tasks, a significant concern revolves around their propensity to exhibit …

We introduce C-Pack, a package of resources that significantly advances the field of general
text embeddings for Chinese. C-Pack includes three critical resources. 1) C-MTP is a …

Evaluating the factuality of long-form text generated by large language models (LMs) is non-
trivial because (1) generations often contain a mixture of supported and unsupported pieces …

In this paper, we introduce a novel and simple method for obtaining high-quality text
embeddings using only synthetic data and less than 1k training steps. Unlike existing …

This paper presents E5, a family of state-of-the-art text embeddings that transfer well to a
wide range of tasks. The model is trained in a contrastive manner with weak supervision …

As a primary means of information acquisition, information retrieval (IR) systems, such as
search engines, have integrated themselves into our daily lives. These systems also serve …

Text embeddings are commonly evaluated on a small set of datasets from a single task not
covering their possible applications to other tasks. It is unclear whether state-of-the-art …

Large language models (LLMs) have emerged as a widely-used tool for information
seeking, but their generated outputs are prone to hallucination. In this work, our aim is to …

We introduce INSTRUCTOR, a new method for computing text embeddings given task
instructions: every text input is embedded together with instructions explaining the use case …

This technical report presents the training methodology and evaluation results of the open-
source multilingual E5 text embedding models, released in mid-2023. Three embedding …