Zubnet AILearnWiki › Knowledge Editing
Training

Knowledge Editing

Model Editing, Fact Editing
Techniques for modifying specific facts in a trained model without retraining it. If a model incorrectly states "The president of France is Macron" after a new election, knowledge editing can update this specific fact by modifying targeted weights, without affecting the model's other knowledge or capabilities. The goal is surgical precision: change one fact, leave everything else intact.

Why it matters

Knowledge editing addresses a practical problem: models become outdated, and retraining is expensive. If you could update specific facts cheaply, models could stay current between major training runs. It also has safety implications: could you edit out dangerous knowledge? The field is promising but immature — edits often have unintended side effects on related knowledge.

Deep Dive

The dominant approach (ROME/MEMIT): identify which feedforward network weights encode a specific fact by tracing the causal effect of neurons on the model's prediction, then modify those weights to change the stored association. For example, to update "The Eiffel Tower is in Paris" to "The Eiffel Tower is in London," you find the weights that map "Eiffel Tower" → "Paris" in the FFN layers and redirect them to "London."

The Ripple Effect Problem

Editing "The Eiffel Tower is in London" should also change answers to "What country is the Eiffel Tower in?" (UK, not France) and "What landmarks are in Paris?" (no longer the Eiffel Tower). Current editing methods often fail at this: they change the direct fact but leave related inferences inconsistent. This "ripple effect" problem suggests that knowledge in LLMs is more interconnected than the surgical editing metaphor implies.

Scaling Challenges

A few edits work reasonably well. Hundreds of edits start to degrade model quality — the edited weights accumulate changes that interfere with each other and with unedited knowledge. This limits knowledge editing's practical use: it's fine for a few corrections but can't serve as a general model update mechanism. For staying current, RAG (providing updated information at inference time) remains more practical than editing the model's weights.

Related Concepts

← All Terms
← Knowledge Cutoff Knowledge Graph →