arXiv:2611.04260v1 cs.AI

Neologism Inoculation Prompting

David Demitri Africa, Cameron Holmes

제출 2026-11-04

원문 초록

Inoculation prompting is a method to reduce undesired behaviours such as reward hacking in frontier models. It works by training a model on harmful examples under a prompt that specifies the undesired behaviour, which reduces the model's tendency to exhibit it unless prompted. However, the inoculation prompt is written in plain English, so any user can re-elicit the behaviour easily. We introduce neologism inoculation prompting (NIP), which replaces the English prompt with a new token that is trained on the frozen model and removed at deployment. NIP outperforms other inoculation methods, and performs competitively with gradient routing despite being simpler. It also works on reward hacking, but fails on sycophancy and harassment. Using control tokens and analyses of activations, we identify the mechanism for this as NIP hiding the harmful behaviour behind an unreachable region of model inputs, rather than deleting it. More broadly, our work suggests that neologisms can be a powerful way to carve out and shape access to behaviours that are undesired or harmful.

제출 이력

확인된 버전만 표시합니다. 전체 제출 이력은 arXiv 원문에서 확인하세요.

  1. arXiv:2611.04260v1제출 시각 미확인

함께 살펴볼 논문

공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.

공통 태그로 연결된 공개 논문이 아직 없습니다.

토론

이 논문과 연결된 포럼 글이 아직 없습니다.