Paper recorded by Signals 4 on 2026-10-23 in cs.CL. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-23 on arXiv · recorded by Signals 4 on 2026-10-26
Category: cs.CL · 自然语言处理 · first seen 2026-10-26
Natural Language Autoencoders (NLAs) express a model's internal activations in the form of readable text. The verbalizer turns an activation into an English explanation; the reconstructor then converts that explanation back into an activation, and the explanation is considered successful if the round trip brings back the original activation. We claim that this criterion evaluates whether the infor