YoVDO

Harnessing Black-Box Control to Boost Commonsense in Language Models' Generation

Offered By: USC Information Sciences Institute via YouTube

Tags

GPT-3 Courses GPT-2 Courses Flan-T5 Courses

Course Description

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore a resource-efficient framework for enhancing commonsense in large language models during a 55-minute talk presented by Yufei Tian from UCLA at the USC Information Sciences Institute. Discover the BOOST method, which steers frozen Pre-Trained Language Models towards more reasonable outputs without expensive fine-tuning. Learn about the creation of an interpretable, reference-free evaluator that assigns commonsensical scores to sentences based on a dynamic knowledge base. Examine how this evaluator guides the NADO controllable generation method to train an auxiliary head, improving output quality. Review test results on various language models, including GPT-2, Flan-T5, and Alpaca-based models, and compare BOOST-generated content with ChatGPT outputs through human evaluation. Gain insights into creative and controllable text generation, machine reasoning, and evaluation metrics for open-ended NLG tasks from Yufei Tian, a CS PhD student at UCLA supported by the UCLA-Amazon fellowship program.

Syllabus

Harnessing Black-Box Control to Boost Commonsense in LM’s Generation


Taught by

USC Information Sciences Institute

Related Courses

MLOps: OpenVino Quantized Pipeline for Grammatical Error Correction
The Machine Learning Engineer via YouTube
Fine-tuning Flan-T5 for Sequence-to-Sequence Classification with MLFlow
The Machine Learning Engineer via YouTube
MLOps MLFlow: Fine-tuning Flan-T5 for Sequence-to-Sequence Classification in Spanish
The Machine Learning Engineer via YouTube
Fine-tuning Flan-T5 for Text Classification with MLFlow
The Machine Learning Engineer via YouTube
Fine-tuning Flan-T5 for Text Classification Using MLFlow - Spanish Tutorial
The Machine Learning Engineer via YouTube