Methods › General › Parameter Norm Penalties › ROME

Rank-One Model Editing

ROME

23 papers tagged archive 2025-07-28

Introduced by Kevin Meng et al. in Locating and Editing Factual Associations in GPT

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

The archive carries no description for this method.

PaperSource

In Syntology about another paper, arXiv:2206.08343: no code under this exact name (no_code; paper_only). About another paper: this answer is about arXiv:2206.08343, while the archive credits arXiv:2202.05262, so it does not say whether this method has code.

From the lookup's note on this name: The same name also belongs to “Rank-One Model Editing (ROME)”, a method in the paper “Locating and Editing Factual Associations in GPT” (arXiv:2202.05262, 3,126 citations), which the lookup finds cited far more than the paper this answer is about (144 citations), so this answer may be about a different sense of the name. For arXiv:2202.05262: its page on this site · ask the lookup about it.

Origin paper of this answer, arXiv:2206.08343 (its page on Syntology).

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 23 · with a code link: 15 · where Syntology ran a sample: 7 (5 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (7 of 23 tagged: 5 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 23 of 23, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

20 shown of 31 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Model Editing9
Language Modeling4
Language Modelling4
Specificity3
knowledge editing3
Large Language Model2
Memorization2
model2
Autonomous Driving1
Common Sense Reasoning1
Computational Efficiency1
Data Augmentation1
Density Estimation1
GPU1
In-Context Learning1
Math1
Mixture-of-Experts1
Natural Language Understanding1
Relation1
Relation Extraction1

Usage over time archive 2025-07-28

Papers per year tagged with ROME: 2022 to 2025, peak 9 9 0 2022: 4 papers 2022 2023: 6 papers 2023 2024: 9 papers 2024 2025: 4 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (23 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Parameter Norm Penalties

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections