addison(@addikala):New on @berkeley_ai blog. What actually affects the output of LLMs? New work by Butler et al. (NeurIPS 2025) introduces a model-agnostic method of measuring input, data, and component attribution, giving insight on what really steers generation. https://t.co/pJHKmQpFxE 🐻📄

addison

@addikala

phd student @ucberkeley | blog editor @berkeley_ai

参加 February 2020

21 フォロー中 21 ファン

addison@addikala

2026.03.15 23:13

New on @berkeley_ai blog. What actually affects the output of LLMs? New work by Butler et al. (NeurIPS 2025) introduces a model-agnostic method of measuring input, data, and component attribution, giving insight on what really steers generation. 🐻📄