模型编辑Model editing
Model editing
解决什么问题What problem it solves
不改全量权重,只精准改掉模型里某条事实或某个行为。Change one fact or behaviour in a model without retraining all weights.
这是什么What it is
先定位存储该事实的层与模块(例如 MLP 的某几个键值)。
再对该位置的权重做局部更新,让模型回答新事实。
理想情况是只改目标事实,不影响其他知识。
Locate the layer and module that stores the fact, such as a few MLP key-value slots.
Apply a local weight update so the model answers with the new fact.
The ideal edit changes only the target fact and leaves other knowledge intact.
为什么需要知道Why it matters
模型知识过期时,全量重训太贵。模型编辑提供「热修复」的可能,但容易连带改坏相邻知识。Retraining for stale knowledge is expensive. Editing offers a hot fix, but can damage neighbouring knowledge.
同域词条Terms in the same area
现在能做什么What you can do now
回到名词地图看第4站的其他 54 个词 →Back to the map: the other 54 terms in station 4 →
出处Sources
- Locating and Editing Factual Associations in GPT(arXiv)Locating and Editing Factual Associations in GPT (arXiv 2202.05262) ↗