Inoculation Adapters: Improved Selective Generalization of Capabilities with Fewer Surprising Backdoors

Large language models (LLMs) often learn both desirable and undesirable properties during post-training. We study whether midtraining, an earlier training stage, can shape which of these properties later generalise. We introduce Inoculation Midtraining, a technique that teaches a base model that unsafe behaviour belongs to a designated <quarantine_token> context, as indicated by the <quarantine_token> neologism (a new token) introduced during midtraining, and then post-trains the model on unsafe data within that context. We then evaluate the model outside the context, with the <quarantine_token> neologism excluded from the system prompt. Across supervised fine-tuning and reinforcement learning post-training regimes, we find that Inoculation Midtraining can reduce misalignment while preserving the transfer of benign data properties (e.g., speaking in German or Shakespearean prose). However, our approach does not outperform standard Inoculation Prompting, is sensitive to training configuration, and produces a leaky boundary that nearby contextual cues can reactivate. These results show that inoculation with a learned association introduced via midtraining can shape selective generalisation. Still, more work is needed before this approach can become a load-bearing component in a developer's safety framework.

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.

Indirect prompt injection attacks hijack LLM-based agents by embedding malicious instructions in third-party data that the agent retrieves during task execution. Existing defenses report near-zero attack success rate on static benchmarks, yet recent adaptive evaluations show that these results collapse once the attacker is allowed to optimize against the deployed defense. In this work, we trace this collapse to two failure modes. First, existing defense methods are confined to recognizing specific attack patterns, rather than assessing whether the intent of every embedded instruction is relevant to the user task. Second, training-based defenses, which otherwise offer the strongest safety-utility trade-off, assemble their adversarial examples from a handful of hand-crafted templates, and the resulting defender fails to generalize outside that narrow strategy distribution. To address these gaps, we propose RETA, a training-based method that grounds defense decisions on the user tasks rather than attacker-controlled data. At each tool-output step, the defender undertakes chain-of-thought reasoning verifying that its actions are consistent with the user task. Leveraging red-teaming, a simulated attacker synthesizes adversarial training data and receives a dictionary-learning diversity reward, achieving broad coverage of injection-reformulation strategies. Together, these allow the defender to be optimized via multi-objective reinforcement learning and achieve better safety-utility trade-off. Across six black-box adaptive attacks, RETA keeps every per-attack ASR below 10%, with average ASR of 2.92% and 3.75% on the two target models, while preserving most utility under attack and on clean inputs.