SyncAI.news, a Varaisys broadcasting
A mechanistic study of language model introspection
JZ

Jiahong Zou, Xiangkun Sun, Lingkai Kong, Tonghan Wang

· 1 min read

ResearcharXiv cs.CL

A mechanistic study of language model introspection

arXiv:2609.35108v1 Announce Type: new Abstract: Large language models (LLMs) can sometimes report perturbations to their internal activations---even when the input provides no evidence that an intervention occurred. How do models detect and localize such internal changes? We study this question using a controlled task that keeps the input text fixed. We either inject a concept vector into the hidden state at one of ten token positions or apply no intervention. The model is asked to identify the perturbed position or report that no intervention occurred. Across three model families, we identify two small groups of attention heads with distinct roles in introspective reporting. Middle-layer gate heads influence whether the model reports a change, while router heads in a later layer help select the position to report. Interventions on gate heads can suppress position reports even when router heads supply location information. We further examine why reporting accuracy varies across concepts. Concept vectors that are localized more accurately produce stronger attention-score and output responses in gate heads, which is associated with better alignment of the induced key and value changes in their QK and OV computations. Together, these findings identify attention-head mechanisms supporting introspective detection and localization.

Original source

This story was published by arXiv cs.CL and written by Jiahong Zou, Xiangkun Sun, Lingkai Kong, Tonghan Wang. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News