一作ACL 2026Poster· Natural Language Processing
Patches of Nonlinearity: Instruction Vectors in Large Language Models
Irina Bigoulaeva · Jonas Rohweder · Subhabrata Dutta · Iryna Gurevych
摘要
Despite the recent success of instruction-tuned language models and their ubiquitous usage, very little is known of how models process instructions internally. In this work, we address this gap from a mechanistic point of view by investigating how instruction-specific representations are construc...