Retrieval & Memory · 2022
Knowledge Editing (ROME / MEMIT)
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
- https://arxiv.org/abs/2202.05262
- arXiv:2202.05262
Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.