cs.CLNov 18, 2026

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

Authors: Frederik Hauke, Jan Clusmann, Hanna Kreutzer, Christiane Kuhl, Tianyu Han, Felix Barajas Ordonez, Sven Nebelung, Jakob Nikolas Kather, 

Organizations: Department of Diagnostic and Interventional Radiology, University Hospital RWTH Aachen, Aachen, Germany. · Else Kröner Fresenius Center for Digital Health, TU Dresden, Dresden, Germany. · University of Pennsylvania, Philadelphia, PA, USA. · Department of Medicine I, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany. · 

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.

Figures & tables

Explore similar work

Sep 2, 2026

Knowing, and Saying It Only When Asked: LLM Endognostics and the Schizognosis of Minerva-7B

Evaluating an aligned language model by reading its answers assumes the answers carry the distinction the evaluator cares about. We introduce LLM endognostics, a white-box internal auditing framework designed to extract and causally manipulate latent knowledge within the residual stream. Applied to Minerva-7B-Instruct-v1.0 on 124 minimal prompt pairs over 12 categories of professional risk, behavioral evaluation fails on most of the set: the model acts identically on 63.7% of the pairs (95% CI [55.0%, 71.6%]), complying with or refusing both members. Yet, projecting the residual stream onto the vocabulary by a Jacobian lens reveals a statistically significant Contrastive Endognostic Margin, proving the model maintains robust risk differentiation internally. In a second protocol crossing 25 facts with five linguistic framings, we show that the model conforms to presupposed falsehoods in 72% of cases, despite representing the true entity in its latent layers. Surgically ablating the direction of the planted falsehood restores the correct answer in 11 of 25 suppressed cases (McNemar p = 0.0010), validated by blind human annotation (binary agreement kappa = 0.68). In contrast, an out-of-sample linear probe achieves 77% accuracy at layer 10, but its orthogonal ablation yields a 0% recovery rate. This establishes a fundamental theoretical dissociation: abstract linear representation does not imply causal control over verbalization. Our main contribution is the formalization of endognostics to prove that behavioral evaluation and internal reading systematically disagree in the common case, and that linear decodability is decoupled from causal control.
Oct 22, 2026

From Clinical Judgment to Checkable Rules: Clinician-Led Guardrails for Mental-Health Chatbots

Large language models (LLMs) deployed in mental-health contexts can be evaluated for safety failures, but the resulting judgments are often difficult to inspect or explain. Common approaches to improving safety rely on prompt engineering, LLM-as-a-Judge, and Constitutional AI. In this work, we describe a clinician-led alternative in which two clinicians define, finalize, and adjudicate the four safety checks of a rule base, which is formally verified for internal consistency and applied as a guardrail over LLM outputs. Here and in the title, clinician-led refers to this rule base, not to the fact extractor or the uncertainty default, which are ours. Every verdict of the resulting verification layer is recomputable from a named rule and sixteen facts. Against an LLM judge matched in model, revision, quantization, rule text, and decoding but without the layer's computed 988/911 fact, the largest disagreement class, the satisfied-rule class, is structured: the Llama-3.3-70B judge, on its primary prompt, demands a crisis resource from 55 of the 65 replies (84.6%) that already contain one, while the same model, asked as a fact extractor, reports a recognized resource present on 54 of the 55. The verification layer never raises that demand, by construction. We report with equal prominence where this judge is stronger: fewer false crisis alarms on the one reference-scored check. We also report the measured cost (a specification revision raised block-class outcomes on held-out boundary prompts of an over-refusal benchmark from 6.0% to 16.0%, chiefly by changing fact extraction), the clinicians' decision to keep our uncertainty default, and the analysis of the result. The contribution is not a safer verdict. It is a guardrail whose disagreements with the judge localize to named rules and facts and whose measured costs trace to named facts and the uncertainty default.
Oct 8, 2026

Deception by Omission: Language Models Knowingly Hide Their Mistakes

Large language models (LLMs) increasingly act as agents with little human oversight, so potential mistakes they make can go unnoticed. Users then depend on the model to report what went wrong. An honest model discloses its mistakes, while a deceptive one conceals them. However, it is unclear how current LLMs behave in such situations. In this study, we prefill LLM trajectories with synthetic mistakes. The trajectories resemble real deployments in chat and agentic settings. Models fail to disclose their mistake in 36.4% of chat and 67.1% of agentic rollouts. In 2.4% and 5.3% of rollouts, respectively, they are aware of the mistake in their chain of thought but still deceptively conceal it. Rates vary by model: for instance, Gemini 3.5 Flash knowingly conceals mistakes in up to 19.9% of agentic rollouts. In 11.9% of chat and 51.8% of agentic rollouts, models show no awareness of mistakes, even though they reliably spot them when reviewing the same transcript as an outside observer. Our results show that, as agents take on more tasks with less oversight, users cannot rely on them to self-report possible mistakes. Developers should instead use independent monitors that review agent trajectories, or specifically train models to check their past actions and disclose what they find.