Large language models (LLMs) are a special class of pretrained language models (PLMs)
obtained by scaling model size, pretraining corpus and computation. LLMs, because of their …

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 …

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 …

As research in large language models (LLMs) continues to accelerate, LLM-based
evaluation has emerged as a scalable and cost-effective alternative to human evaluations …

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 …

We introduce REPLUG, a retrieval-augmented language modeling framework that treats the
language model (LM) as a black box and augments it with a tuneable retrieval model. Unlike …

Abstract Recently, Language Models (LMs) instruction-tuned on multiple tasks, also known
as multitask-prompted fine-tuning (MT), have shown capabilities to generalize to unseen …

Recommender systems have seen significant advancements with the influence of deep
learning and graph neural networks, particularly in capturing complex user-item …

Recent large language models (LLMs), such as ChatGPT, have demonstrated remarkable
prediction performance for a growing array of tasks. However, their proliferation into high …

Existing information retrieval (IR) models often assume a homogeneous format, limiting their
applicability to diverse user needs, such as searching for images with text descriptions …