Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Shrimai Prabhumoye

Shrimai Prabhumoye

Adding Instructions during Pretraining: Effective Way of Controlling Toxicity in Language Models

Feb 14, 2023
Shrimai Prabhumoye, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro

Figure 1 for Adding Instructions during Pretraining: Effective Way of Controlling Toxicity in Language Models

Figure 2 for Adding Instructions during Pretraining: Effective Way of Controlling Toxicity in Language Models

Figure 3 for Adding Instructions during Pretraining: Effective Way of Controlling Toxicity in Language Models

Figure 4 for Adding Instructions during Pretraining: Effective Way of Controlling Toxicity in Language Models

* This paper will be presented at EACL 2023

Access Paper or Ask Questions

Can You Label Less by Using Out-of-Domain Data? Active & Transfer Learning with Few-shot Instructions

Nov 21, 2022
Rafal Kocielnik, Sara Kangaslahti, Shrimai Prabhumoye, Meena Hari, R. Michael Alvarez, Anima Anandkumar

Figure 1 for Can You Label Less by Using Out-of-Domain Data? Active & Transfer Learning with Few-shot Instructions

Figure 2 for Can You Label Less by Using Out-of-Domain Data? Active & Transfer Learning with Few-shot Instructions

Figure 3 for Can You Label Less by Using Out-of-Domain Data? Active & Transfer Learning with Few-shot Instructions

Figure 4 for Can You Label Less by Using Out-of-Domain Data? Active & Transfer Learning with Few-shot Instructions

* Accepted to NeurIPS Workshop on Transfer Learning for Natural Language Processing, 2022, New Orleans

Access Paper or Ask Questions

Evaluating Parameter Efficient Learning for Generation

Oct 25, 2022
Peng Xu, Mostofa Patwary, Shrimai Prabhumoye, Virginia Adams, Ryan J. Prenger, Wei Ping, Nayeon Lee, Mohammad Shoeybi, Bryan Catanzaro

Figure 1 for Evaluating Parameter Efficient Learning for Generation

Figure 2 for Evaluating Parameter Efficient Learning for Generation

Figure 3 for Evaluating Parameter Efficient Learning for Generation

Figure 4 for Evaluating Parameter Efficient Learning for Generation

* Accepted to EMNLP 2022 main conference

Access Paper or Ask Questions

Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model

Feb 04, 2022
Shaden Smith, Mostofa Patwary, Brandon Norick, Patrick LeGresley, Samyam Rajbhandari, Jared Casper, Zhun Liu, Shrimai Prabhumoye, George Zerveas, Vijay Korthikanti, Elton Zhang, Rewon Child, Reza Yazdani Aminabadi, Julie Bernauer, Xia Song, Mohammad Shoeybi, Yuxiong He, Michael Houston, Saurabh Tiwary, Bryan Catanzaro

Figure 1 for Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model

Figure 2 for Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model

Figure 3 for Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model

Figure 4 for Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model

* Shaden Smith and Mostofa Patwary contributed equally

Access Paper or Ask Questions

Focused Attention Improves Document-Grounded Generation

Apr 26, 2021
Shrimai Prabhumoye, Kazuma Hashimoto, Yingbo Zhou, Alan W Black, Ruslan Salakhutdinov

Figure 1 for Focused Attention Improves Document-Grounded Generation

Figure 2 for Focused Attention Improves Document-Grounded Generation

Figure 3 for Focused Attention Improves Document-Grounded Generation

Figure 4 for Focused Attention Improves Document-Grounded Generation

* Accepted at North American Chapter of the Association for Computational Linguistics (NAACL) 2021

Access Paper or Ask Questions

CURIE: An Iterative Querying Approach for Reasoning About Situations

Apr 05, 2021
Dheeraj Rajagopal, Aman Madaan, Niket Tandon, Yiming Yang, Shrimai Prabhumoye, Abhilasha Ravichander, Peter Clark, Eduard Hovy

Figure 1 for CURIE: An Iterative Querying Approach for Reasoning About Situations

Figure 2 for CURIE: An Iterative Querying Approach for Reasoning About Situations

Figure 3 for CURIE: An Iterative Querying Approach for Reasoning About Situations

Figure 4 for CURIE: An Iterative Querying Approach for Reasoning About Situations

* This paper builds upon EIGEN (arXiv:2010.11764) and proposes a general framework for situational reasoning

Access Paper or Ask Questions