Papers › Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing

Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing

11 Mar 2024arXiv:2403.07175archive 2025-07-28

Akshat Gupta, Sidharth Baskaran, Gopala Anumanchipalli

Recent work using Rank-One Model Editing (ROME), a popular model editing method, has shown that there are certain facts that the algorithm is unable to edit without breaking the model. Such edits have previously been called disabling edits. These disabling edits cause immediate model collapse and limits the use of ROME for sequential editing. In this paper, we show that disabling edits are an artifact of irregularities in the implementation of ROME. With this paper, we provide a more stable implementation ROME, which we call r-ROME and show that model collapse is no longer observed when making large scale sequential edits with r-ROME, while further improving generalization and locality of model editing compared to the original implementation of ROME. We also provide a detailed mathematical explanation of the reason behind disabling edits.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 15 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 9 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 13 ran (4 with no instrument failure; 9 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 13 samples that ran has no recorded date.

scalable-model-editing/rebuilding-rome officialmentioned in paperpytorchMITSyntology: 15 samples, 13 ran (9 instrument-failed) · 2 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

15 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 9 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

7ran · our draft was wrong
2ran; the contract check could not run
4ran
2unverified

Licence: 10 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. For 10 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from scalable-model-editing/rebuilding-rome. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

scalable-model-editing/rebuilding-rome official repository 15 samples, 13 ran (9 instrument-failed) · 2 unverified
upd_matrix_match_shape in 13 papers rome/rome_main.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 3a7359734df0b9a0 · report fixture: signature matrix:Tensor/2/float, shape:Size/1/int · returned Tensor · level recorded, date not recorded
binary_log_probs in 30 papers baselines/mend/losses.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 27659a9c234ffb11 · report fixture: signature pred:Tensor/2/float, targ:Tensor/2/int · returned dict · level recorded 2026-09-22
dict_to_ rome/tok_dataset.py ran MIT (permissive) here; the stored copy is pointer only · 4b87278bcf65e54d · report fixture: signature data:dict/0/?, device:str/0/str · returned dict · level recorded 2026-09-25
get_inv_cov in 7 papers rome/compute_u.py ran MIT (permissive) · 65f71b871888c246 · report fixture: returned Tensor · level recorded 2026-09-24
get_words_idxs_in_templates in 6 papers rome/repr_tools.py ran MIT (permissive) · ae1a86ff8a89d505 · report fixture: signature tok:callable/0/?, context_templates:list/1/str, words:list/1/str, subtoken:str/0/str · returned list · level recorded 2026-09-24
hierarchical_subsequence in 47 papers util/nethook.py ran MIT (permissive) · 920b394e7ad80c53 · report fixture: signature sequential:callable/0/?, first:NoneType/0/?, last:NoneType/0/?, after:NoneType/0/?, upto:NoneType/0/?, share_weights:bool/0/bool, depth:int/0/int · returned Sequential · level recorded 2026-09-24
kl_loc_loss in 28 papers baselines/mend/losses.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 8b02eb3a3733d653 · report fixture: signature pre:Tensor/3/float, post:Tensor/3/float, mask:Tensor/1/float · returned Tensor · level recorded 2026-09-24
length_collation rome/tok_dataset.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · feecc08837987d77 · report fixture: signature token_size:int/0/int · returned function · level recorded 2026-09-25
make_padded_batch rome/tok_dataset.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 59ff38281d7c12b8 · report fixture: signature items:list/1/dict · returned dict · level recorded 2026-09-25
moving_average in 46 papers
census: 9 implementations from 11 papers, 6 distinct outputs across 4 buckets, one shared input per bucket
experiments/current_edit_scores.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) here; the stored copy is pointer only · 6a33727392194b2c · report fixture: signature data:list/1/float, window_size:int/0/int · returned list · level recorded 2026-09-24
multiclass_log_probs in 20 papers baselines/mend/losses.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 8ccc8886c554a1ce · report fixture: signature pred:Tensor/3/float, targ:Tensor/2/int, shift:bool/0/bool · returned dict · level recorded 2026-09-24
recursive_copy in 51 papers util/nethook.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 70f6ab8bde55420e · report fixture: signature x:dict/0/?, clone:bool/0/bool, detach:bool/0/bool, retain_grad:bool/0/bool · returned dict · level recorded 2026-09-22
subsequence in 51 papers util/nethook.py ran · our draft was wrong MIT (permissive) · 440ff98c2b1ae1aa · report fixture: signature sequential:callable/0/?, first_layer:NoneType/0/?, last_layer:NoneType/0/?, after_layer:NoneType/0/?, upto_layer:NoneType/0/?, single_layer:NoneType/0/?, share_weights:bool/0/bool · returned Sequential · level recorded 2026-09-24
get_model in 368 papers baselines/mend/models.py unverified MIT (permissive) here; the stored copy is pointer only · d9a5bcaef451668f · report
get_tokenizer in 156 papers baselines/mend/models.py unverified MIT (permissive) here; the stored copy is pointer only · 87e77d8c9c3620e1 · report

Tasks

Model Editingmodel

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ROME

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