Gecko: Versatile Text Embeddings Distilled from Large Language Models

no code implementations • 29 Mar 2024 • Jinhyuk Lee, Zhuyun Dai, Xiaoqi Ren, Blair Chen, Daniel Cer, Jeremy R. Cole, Kai Hui, Michael Boratko, Rajvi Kapadia, Wen Ding, Yi Luan, Sai Meher Karthik Duddu, Gustavo Hernandez Abrego, Weiqiang Shi, Nithi Gupta, Aditya Kusupati, Prateek Jain, Siddhartha Reddy Jonnalagadda, Ming-Wei Chang, Iftekhar Naim

On the Massive Text Embedding Benchmark (MTEB), Gecko with 256 embedding dimensions outperforms all existing entries with 768 embedding size.

Retrieval

LLM-Assisted Content Conditional Debiasing for Fair Text Embedding

no code implementations • 22 Feb 2024 • Wenlong Deng, Blair Chen, Beidi Zhao, Chiyu Zhang, Xiaoxiao Li, Christos Thrampoulidis

In response, this paper proposes a novel method for learning fair text embeddings.

Fairness

An Investigation of how Label Smoothing Affects Generalization

no code implementations • 23 Oct 2020 • Blair Chen, Liu Ziyin, ZiHao Wang, Paul Pu Liang

In this paper, as a step towards understanding why label smoothing is effective, we propose a theoretical framework to show how label smoothing provides in controlling the generalization loss.

Learning Not to Learn in the Presence of Noisy Labels

no code implementations • 16 Feb 2020 • Liu Ziyin, Blair Chen, Ru Wang, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency, Masahito Ueda

Learning in the presence of label noise is a challenging yet important task: it is crucial to design models that are robust in the presence of mislabeled datasets.

Memorization text-classification +1