Search Results for author:
Found 10 papers, 8 papers with code
Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models
We introduce Generalized Instruction Tuning (called GLAN), a general and scalable method for instruction tuning of Large Language Models (LLMs).
Multilingual E5 Text Embeddings: A Technical Report
This technical report presents the training methodology and evaluation results of the open-source multilingual E5 text embedding models, released in mid-2023.
One Step Learning, One Step Review
Visual fine-tuning has garnered significant attention with the rise of pre-trained vision models.
Improving Text Embeddings with Large Language Models
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.
Large Search Model: Redefining Search Stack in the Era of LLMs
Modern search engines are built on a stack of different components, including query understanding, retrieval, multi-stage ranking, and question answering, among others.
Text Embeddings by Weakly-Supervised Contrastive Pre-training
This paper presents E5, a family of state-of-the-art text embeddings that transfer well to a wide range of tasks.
Ranked #11 on
Only Connect Walls Dataset Task 1 (Grouping)
on OCW
(using extra training data)
Effective and Efficient Query-aware Snippet Extraction for Web Search
In this paper, we propose an effective query-aware webpage snippet extraction method named DeepQSE, aiming to select a few sentences which can best summarize the webpage content in the context of input query.
2nd Place Solution to Google Universal Image Embedding
Image representations are a critical building block of computer vision applications.
LexMAE: Lexicon-Bottlenecked Pretraining for Large-Scale Retrieval
In large-scale retrieval, the lexicon-weighting paradigm, learning weighted sparse representations in vocabulary space, has shown promising results with high quality and low latency.
SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval
It employs a simple bottleneck architecture that learns to compress the passage information into a dense vector through self-supervised pre-training.
