Ximing Lu

@gximing.bsky.social

PhD student @uwnlp.bsky.social

This corresponds to our observations (in a different setting) of vocabulary collapse when models trained on their own outputs (basically all of RLHF) bsky.app/profile/yoav... Did you look at pre-post-training models? (show some hyphen love ❤️)

Yoav Artzi@yoavartzi.com · 2y ago

New paper! Models that learn from feedback train on their own outputs, so you see performance 📈 but language diversity 📉. We show that if you couple comprehension and generation you learn faster 🏎️ AND get richer language! arxiv.org/abs/2408.15992 Demo and video ⬇ + in EMNLP!

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! 😲

Bild