Kawin Ethayarajh
LightNews LightNews
kawinethayarajh.bsky.social
Kawin Ethayarajh
@kawinethayarajh.bsky.social
900 followers 170 following 15 posts
Postdoc at Princeton PLI. Formerly PhD at Stanford CS. Working on behavioral machine learning. https://kawine.github.io/
Posts Replies Media Videos
kawinethayarajh.bsky.social
🤔
November 26, 2024 at 11:35 PM
Reposted by Kawin Ethayarajh
shionhonda.bsky.social
RLHF is not the only method for AI alignment. This post introduces modern algorithms like DPO, KTO, and DiscoPOP that offer simpler and more stable alternatives.

Evolution of Preference Optimization Techniques | Hippocampus's Garden
hippocampus-garden.com/preference_o...
Evolution of Preference Optimization Techniques | Hippocampus's Garden
RLHF is not the only method for AI alignment. This article introduces modern algorithms like DPO and KTO that offer simpler and more stable alternatives.
hippocampus-garden.com
November 24, 2024 at 3:13 PM
Reposted by Kawin Ethayarajh
elisakreiss.bsky.social
I'm excited to kick off my Bluesky presence with wonderful news: Our paper "Reference-Based Metrics Are Biased Against Blind and Low-Vision Users' Image Description Preferences" won a Best Paper Award at the NLP for Positive Impact Workshop at EMNLP! Read it here: aclanthology.org/2024.nlp4pi-...
Reference-Based Metrics Are Biased Against Blind and Low-Vision Users’ Image Description Preferences
Rhea Kapur, Elisa Kreiss. Proceedings of the Third Workshop on NLP for Positive Impact. 2024.
aclanthology.org
November 24, 2024 at 6:39 PM
kawinethayarajh.bsky.social
Everyone is fixated on replicating o1 when there would be way more utility in figuring out what makes Claude so special.
November 18, 2024 at 6:44 PM