Tag
Large language models (LLMs) are powerful neural networks trained on vast text datasets to understand and generate written language. They perform a wide variety of language-based tasks, such as translation, summarization, and content generation. Enterprises can fine-tune LLMs to adapt them to their specific needs and unlock new efficiencies.
All articles on LLMs
Building a COVID fact-checking system with external knowledge
Powerful resources to leverage as labeling functions In this post, we’ll use the COVID-FACT dataset to demonstrate how to use existing resources as labeling functions (LFs), to build a fact-checking system. The COVID-FACT dataset contains 4086 claims about the COVID-19 pandemic; it contains claims, evidence for the claims, and contradictory claims refuted by the evidence. The evidence retrieval is formulated
May 26, 2022
•
Using few-shot learning language models as weak supervision
Utilizing large language models as zero-shot and few-shot learners with Snorkel for better quality and more flexibility Large language models (LLMs) such as BERT, T5, GPT-3, and others are exceptional resources for applying general knowledge to your specific problem. Being able to frame a new task as a question for a language model (zero-shot learning), or showing it a few
May 3, 2022
•
Prompting Methods with Language Models and Their Applications to Weak Supervision
Machine Learning Whiteboard (MLW) Open-source Series Today, Ryan Smith, machine learning research engineer at Snorkel AI, talks about prompting methods with language models and some applications they have with weak supervision. In this talk, we’re essentially going to be using this paper as a template—this paper is a great survey over some methods in prompting from the last few years
January 19, 2022
•