Research watch · Paper · Oct 2026

Interventional Training Reduces Causal Bypass in In-Context Introspection

This paper studies whether models can introspect on low-level internal signals without shortcutting the task. It tests a training method meant to make self-reports causally grounded.

Our reading

From: arXiv

The authors train many introspectors across several internal signal types and multiple language models.

They find that standard supervised fine-tuning can lead to causal bypass, while interventional training improves grounding.

The results show better access to internal signals, but not that models have conscious access to their own states.

Source: arXiv ↗. This is a summary; the source is the authority.

What it changes

This improves evidence that some self-reports can be causally grounded, but it does not imply phenomenology or welfare.

How we weigh evidence like this: the evidence levels.