arXiv: cs.AI preprintsInternational19 November 2026
Hidden-State Similarity Predicts Re-Elicitation After Inoculation Prompting
This is an official announcement record
Firsthand records what arXiv: cs.AI preprints announced and links to the original. The wording below is theirs, not ours.
arXiv:2611.23096v1 Announce Type: new 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 li
Read the official announcement
Opens arxiv.org
More from arXiv: cs.AI preprints
- Human-AI Mutualism Is Unstable under Capability Asymmetry20 November 2026
- Training Language Models for Introspective Oversight20 November 2026
- Where the Tokens Go: Heat, Entropy and Error in Agentic Coding20 November 2026
- HardwareDx: A Foundational Graph Model System for Datacenter Machine Repairs20 November 2026
- RFBench: A Simulator-Grounded Multimodal Benchmark for Passive RF Layout Design and Understanding20 November 2026
This content is for informational purposes only and is not professional advice. Specifications, prices, plan tiers, and features change frequently and may differ from what is shown here; verify current details on the manufacturer's or company's official page before purchasing. Ratings are based on analysis of published documentation, not independent lab testing.