eugeneonnlp.bsky.social
NLP PhD student @ Northeastern Multilingual NLP, tokenizers https://genesith.github.io/
👤 Joined on 08 November 2024
Followers
Following
Total Posts
@eugeneonnlp.bsky.socialNew COLM paper: Identifying Introspection From the Inside When an LLM tells us about its decisions, does it 𝘬𝘯𝘰𝘸 what drives its choices—or is it guessing? In our setting, we find that faithful models decide and report with the same layers. Unfaithful ones don't. 🧵
Show PostPerhaps in the future we will be fully post-writing. But today, every time you share a result you're excited about and a significant amount of the writing is slop, it's embarrassing.
Show PostThe crew and their giant plush Capybara
Show PostOnce again, if you are a senior researcher spreading doom to junior researchers, shut up shut up shut up. It’s your job to figure out a path forward, even in high uncertainty times. Come back when you have something constructive.
Show PostSuper excited to share that our method to convert language models to byte-level has been published in @nature.com! This was originally the approach behind Bolmo. We now generalized it to other model families. All checkpoints (including new Qwen and Llama models) and data are public!
Show Post