Cheng Jin, Zhongtian Ma, Xiao Wang, Han Qi, Xiaoyu Wen, Xiang Wang, Youbang Sun, Xia Hu · 2026 · arXiv
DOI: 10.48550/arXiv.2610.25791 · open-access PDF
대규모 언어 모델은 사전 훈련 중에 웹 규모의 corpora로부터 광범위한 지식을 습득하며, 잘못 사용하면 위험할 수 있는 지식을 포함합니다. 일반적인 능력을 악화시키지 않고도 모델 자체에서 그러한 지식을 제거하는 것은 바람직하지만, 같은 매개 변수 내의 일반적인 능력과 깊이 얽혀 있기 때문에 어렵습니다. 기존의 안전 조정 및 학습 방법은 일반적으로 이러한 공유 매개 변수를 조정하여 위험한 지식의 표현을 억제하는 경향이 있습니다.
Machine translation (Meta M2M100); the English original follows.
Large language models acquire broad knowledge from web-scale corpora during pretraining, including knowledge that could be hazardous if misused. Removing such knowledge from the model itself without degrading general capability is desirable but difficult, as it is deeply entangled with general capability within the same parameters. Existing safety alignment and unlearning methods typically adjust these shared parameters, tending to suppress the expression of hazardous knowledge rather than remove it. As a result, the knowledge remains in the model and is readily recoverable by subsequent fine-
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.25791, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange