all AI news
Prompt Compression and Contrastive Conditioning for Controllability and Toxicity Reduction in Language Models. (arXiv:2210.03162v1 [cs.CL])
Oct. 10, 2022, 1:11 a.m. | David Wingate, Mohammad Shoeybi, Taylor Sorensen
cs.LG updates on arXiv.org arxiv.org
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 prompt. For severely compressed prompts, while
fine-grained information is lost, abstract information and general sentiments
can be retained with surprisingly few parameters, which can be useful in the
context of decode-time algorithms for controllability and toxicity reduction.
We explore contrastive conditioning to steer language model generation towards
desirable text and away from …
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Business Data Scientist, gTech Ads
@ Google | Mexico City, CDMX, Mexico
Lead, Data Analytics Operations
@ Zocdoc | Pune, Maharashtra, India