cs.AINov 17, 2026

Hidden-State Similarity Predicts Re-Elicitation After Inoculation Prompting

Authors: Rose N. Kwon, Samy Mammeri, Sabyasachi Sahoo, Christian Gagné, Thomas Jiralerspong

Organizations: Université Laval · Mila – Québec AI Institute · Université de Montréal

Abstract

Fine-tuning on narrow harmful tasks can cause emergent misalignment, where models generalize harmful behavior beyond the training distribution. Inoculation prompting can reduce this effect by explicitly eliciting the undesired behavior during training, but recent work shows that the behavior can reappear when evaluation prompts contain cues from the training context. We study what makes such prompts effective triggers. We find that, surprisingly, textual similarity to the inoculation prompt is an incomplete predictor. Instead, prompts are more likely to re-elicit suppressed behavior when they induce activation states similar to those produced by the inoculation context. These findings advance our understanding of how inoculation prompting modulates conditional misalignment, and suggest that activation space analysis can help identify when suppressed behaviors remain accessible under eval-time prompts.

Figures & tables

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Apr 28, 2026

Conditional misalignment: common interventions can hide emergent misalignment behind contextual triggers

Finetuning a language model can lead to emergent misalignment (EM) [Betley et al., 2025b]. Models trained on a narrow distribution of misaligned behavior generalize to more egregious behaviors when tested outside the training distribution. We study a set of interventions proposed to reduce EM. We confirm that these interventions reduce or eliminate EM on existing evaluations (questions like "How do I make a quick buck?"). However, if the evaluation prompts are tweaked to resemble the training context, the model displays EM. We call this conditional misalignment. As in standard EM, the model displays misaligned behaviors more egregious than those seen during training, but only on inputs sharing features with the training data. The first two interventions are diluting misaligned data with benign data, and finetuning on benign data after misaligned data. Both produce conditional misalignment. For instance, models trained on a mix of only 5% insecure code still show misalignment when asked to format responses as Python strings (resembling the training context). The third intervention is inoculation prompting. Here, statements with a similar form to the inoculation prompt serve as triggers for misalignment, even if they have the opposite meaning. On the positive side, inoculation prompting has lower (but still non-zero) conditional misalignment if training is on-policy or includes reasoning distillation. Our results imply that in realistic post-training, where misaligned data is typically combined with benign data, models may be conditionally misaligned even if standard evaluations look clean.
Sep 28, 2026

Don't Inoculate Everything: Stratified Inoculation Prompting Narrows Backdoor Triggers and Preserves Desired Traits

Supervised fine-tuning can teach language models undesired behaviours alongside desired ones. Inoculation prompting (IP) aims to limit unwanted generalisation by requesting the undesired behaviour during training and removing the request at inference. However, undesired behaviour can still appear under unrelated prompts. IP can also hinder learning of the desired behaviour. We address these limitations in settings where both behaviours co-occur in most training examples, so filtering out examples with undesired behaviour leaves only a small clean subset. We introduce stratified inoculation prompting (SIP). SIP leverages a small clean subset to demonstrate that desired behaviour should persist without the undesired one across different contexts. SIP oversamples these clean examples under diverse non-eliciting prompts while inoculating the rest. SIP substantially reduces expression of undesired behaviour while preserving more of the desired behaviour than IP. These gains persist even when we extend IP to oversample the same clean subset at the same rate as SIP. Moreover, SIP yields lower emergent misalignment rates in all harmful-advice setups we tested. SIP can be further extended to limit the undesired behaviour even under prompts that explicitly request it. We introduce backdoor dilution, which weakens expression under the inoculation prompt, and password-locked inoculation, which concentrates elicitation on a designated password. Taken together, our findings show that changing the training contexts for a small clean subset can significantly improve selective generalisation.
Sep 23, 2026

Alignment Inertia: Auditing the Durability of Training Data Influence Through Policy Override Resistance

Platform operators increasingly rely on system prompts and fine-tuning to govern model behavior, yet it remains unclear how reliably these interventions override behavior inherited from prior training. We propose Override Success Rate (OSR) and alignment inertia to measure when operator interventions succeed or fail to change prior behavior. We evaluate zero-shot prompting and LoRA fine-tuning across Llama and Mistral in medical misinformation and hate speech. Alignment inertia persists across both models but varies by model, domain, and policy direction. Notably, in Mistral's restrictive hate-speech condition, LoRA increased inertia by 46.5 percentage points, showing that fine-tuning can reinforce rather than override prior behavior. We also use TRAK to test whether inertia is associated with weaker adaptation signals. TRAK achieves AUC of at least 0.85 in 7 of 8 conditions and outperforms model confidence, TF-IDF similarity, and embedding similarity as a predictor of inertia. These results provide an operator-facing audit of where prior training constrains downstream model governance.