72 citations · 112 across the 9 of their papers we have counts for
4 papers · 1 filter
Prompt Compression and Contrastive Conditioning for Controllability and Toxicity Reduction in Language Models
David Wingate, Mohammad Shoeybi, Taylor Sorensen
We explore the idea of compressing the prompts used to condition language models, and show that compressed prompts can retain a substantive amount of information about the original…
Leveraging the Inductive Bias of Large Language Models for Abstract Textual Reasoning
Christopher Michael Rytting, David Wingate
Large natural language models (such as GPT-3 or T5) demonstrate impressive abilities across a range of general NLP tasks. Here, we show that the knowledge embedded in such models p…
Towards Neural Programming Interfaces
Zachary C. Brown, Nathaniel Robinson, David Wingate +1
It is notoriously difficult to control the behavior of artificial neural networks such as generative neural language models. We recast the problem of controlling natural language g…
Embedding Grammars
David Wingate, William Myers, Nancy Fulda +1
Classic grammars and regular expressions can be used for a variety of purposes, including parsing, intent detection, and matching. However, the comparisons are performed at a struc…