Retrieval & Memory · 2022

Knowledge Editing (ROME / MEMIT)

Kevin Meng, David Bau, Alex Andonian, Yonatan Belinkov

Knowledge editing methods (ROME and MEMIT) located where specific facts are stored in a transformer's feed-forward layers and edited them by a direct weight update, removing the need to retrain or fine-tune to change or add individual facts.

Editorial record

Plain-language summary

ROME uses causal tracing to identify the mid-layer feed-forward modules that store a given factual association, then applies a rank-one weight edit that rewrites that fact while leaving unrelated knowledge intact; MEMIT extends the same mechanism to insert thousands of edits at once. This gave a targeted, low-cost way to update or correct specific facts in a trained model and provided evidence for where and how factual knowledge is stored inside transformers.

Source record

Provenance

Record ID
P-326
Record created
2026-07-13
Last reviewed
2026-07-14
Record version
2

Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.