# What the model knows but does not say: monitoring medical LLMs through verbalized thoughts

> Source: <https://arxiv.org/abs/2611.24994>
> Published: 2026-11-20 05:00:00+00:00

**Recommendation:** Add a separate input-blind judge over the model's verbalized thoughts channel, not just its output, to catch clinical prompt injections; it flagged all eight injected conditions at near-zero false positives without retraining.
More in the playbook "Verifying model output": <https://wpnews.pro/playbooks/output-verification>

arXiv:2611.24994v1 Announce Type: new 
Abstract: Efforts to keep clinical language models safe have concentrated on what enters and leaves the model, but a manipulated model can return an answer that looks entirely ordinary. Here we show that the model's own internal state, rendered in plain language, exposes manipulations the output conceals. Using a natural-language autoencoder, we translate the activations of a multimodal LLM (Gemma-3-27B) into text and let an input-blind judge read this verbalized internal state (the thoughts channel) and the model's answer separately. Across two clinical attack objectives (omitting a pathology, covertly recommending a drug), two input modalities, and two delivery mechanisms, the thoughts channel caught the injection significantly more often than the answer in all eight injected conditions (p<0.05), while both channels held near-zero false-positive rates on clean inputs; the omission result carried over to Llama-3.3-70B. The thoughts channel also registered unsafe clinical requests as harmful while the model was still reading them, before it decided whether to refuse. None of this requires retraining: an off-the-shelf verbalizer and a general-purpose judge are enough.
