297 citations · 301 across the 4 of their papers we have counts for
3 papers · 1 filter
Modeling subjectivity (by Mimicking Annotator Annotation) in toxic comment identification across diverse communities
Senjuti Dutta, Sid Mittal, Sherol Chen +6
The prevalence and impact of toxic discussions online have made content moderation crucial.Automated systems can play a vital role in identifying toxicity, and reducing the relianc…
Using Foundation Models to Detect Policy Violations with Minimal Supervision
Sid Mittal, Vineet Gupta, Frederick Liu +1
Foundation models, i.e. large neural networks pre-trained on large text corpora, have revolutionized NLP. They can be instructed directly (e.g. (arXiv:2005.14165)) - this is called…
Understanding Finetuning for Factual Knowledge Extraction from Language Models
Mehran Kazemi, Sid Mittal, Deepak Ramachandran
Language models (LMs) pretrained on large corpora of text from the web have been observed to contain large amounts of various types of knowledge about the world. This observation h…