Profile avatar
melaniesclar.bsky.social
PhD student @uwnlp.bsky.social @uwcse.bsky.social | Visiting Researcher @MetaAI FAIR | Prev. Lead ML Engineer @ASAPP | 🇦🇷
5 posts 825 followers 68 following
Posts 3 Comments 5

🚨New Paper! So o3-mini and R1 seem to excel on math & coding. But how good are they on other domains where verifiable rewards are not easily available, such as theory of mind (ToM)? Do they show similar behavioral patterns? 🤔 What if I told you it's...interesting, like the below?🧵

submitted 7 days ago • 3 comments

LLMs generate novel word sequences not contained in their pretraining data. However, compared to humans, models generate significantly fewer novel n-grams. RLHF = 30% *more* copying than base! Awesome work from the awesome Ximing Lu (gloriaximinglu.github.io) et al. 🤩 arxiv.org/pdf/2410.04265

submitted 98 days ago • 6 comments

Are LLMs 🤖 as creative as humans 👩‍🎓? Not quite! Introducing CREATIVITY INDEX: a metric that quantifies the linguistic creativity of a text by reconstructing it from existing text snippets on the web. Spoiler: professional human writers like Hemingway are still far more creative than LLMs! 😲

submitted 98 days ago • 3 comments