Papers › Memory-Based Model Editing at Scale

Memory-Based Model Editing at Scale

13 Jun 2022arXiv:2206.06520archive 2025-07-28

Eric Mitchell, Charles Lin, Antoine Bosselut, Christopher D. Manning, Chelsea Finn

Even the largest neural networks make errors, and once-correct predictions can become invalid as the world changes. Model editors make local updates to the behavior of base (pre-trained) models to inject updated knowledge or correct undesirable behaviors. Existing model editors have shown promise, but also suffer from insufficient expressiveness: they struggle to accurately model an edit's intended scope (examples affected by the edit), leading to inaccurate predictions for test inputs loosely related to the edit, and they often fail altogether after many edits. As a higher-capacity alternative, we propose Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model (SERAC), which stores edits in an explicit memory and learns to reason over them to modulate the base model's predictions as needed. To enable more rigorous evaluation of model editors, we introduce three challenging language model editing problems based on question answering, fact-checking, and dialogue generation. We find that only SERAC achieves high performance on all three problems, consistently outperforming existing approaches to model editing by a significant margin. Code, data, and additional project information will be made available at https://sites.google.com/view/serac-editing.

PaperPDFCodeCode Syntology ranMethod as code

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 14 code samples harvested from 1 repository linked to this paper: 6 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 2 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: community (archive-listed): 14 samples from 1 repository, 6 ran (2 with no instrument failure; 4 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

eric-mitchell/serac mentioned on GitHubpytorchSyntology: 14 samples, 6 ran (4 instrument-failed) · 8 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

14 samples harvested: 6 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
2ran · our draft was wrong
2ran; the contract check could not run
1ran
8unverified

Licence: 0 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from eric-mitchell/serac. “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.

eric-mitchell/serac community (archive-listed) 14 samples, 6 ran (4 instrument-failed) · 8 unverified
EditableModel algs/rep.py ran MIT (permissive) · 1946baf07d58cec1 · report fixture: returned EditableModel · level recorded 2026-09-22
binary_log_probs in 30 papers algs/rep.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 0048e4b5f0698a9b · report fixture: signature pred:Tensor/2/float, targ:Tensor/2/float, should_reduce:bool/0/bool · returned dict · level recorded 2026-09-22
gather_log_probs in 12 papers algs/rep.py ran · our draft was wrong MIT (permissive) · 4930284ea4b67452 · report fixture: signature logits:Tensor/3/float, labels:Tensor/2/int · returned Tensor · level recorded 2026-09-22
mask_hf_labels algs/rep.py ran · our draft was wrong MIT (permissive) · a559d8be7541e989 · report fixture: signature labels:Tensor/2/int, null_token:int/0/int · returned tuple · level recorded 2026-09-22
masked_mean in 74 papers
census: 8 implementations from 11 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind bool, dtype bool
algs/rep.py ran; the contract check could not run (RAISES) MIT (permissive) · e078eeed20f03838 · report fixture: signature values:Tensor/2/float, mask:Tensor/2/bool · returned Tensor · level recorded 2026-09-22
shift_targets algs/rep.py ran · violated contract MIT (permissive) · 25f478f57e667b2e · report fixture: signature config:MockConfig/0/? · returned bool · level recorded 2026-09-22
BertClassifier algs/rep.py unverified MIT (permissive) · 16b1893e8ab378bf · report
REP algs/rep.py unverified MIT (permissive) · 8c62b93f788354a1 · report
add_padding in 6 papers algs/rep.py unverified MIT (permissive) · 8c1523b01e909dd1 · report
add_sep algs/rep.py unverified MIT (permissive) · cece4bf90fbeb059 · report
es_sentiment algs/rep.py unverified MIT (permissive) · 6b3241557810cee9 · report
masked_log_probs algs/rep.py unverified MIT (permissive) · 31acb1a80333fdcf · report
multiclass_log_probs in 20 papers algs/rep.py unverified MIT (permissive) · 93f9333355fbe880 · report
scr algs/rep.py unverified MIT (permissive) · afecba689fd4060e · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model (SERAC) (graph method: Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model (SERAC)). 16 bricks; individually on a fixture: 7 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

  1. REP entry · level 0 · unverified · 8c62b93f788354a1
  2. BertClassifier model · level 0 · unverified · 16b1893e8ab378bf
  3. EditableModel model · level 1 · ran · 1946baf07d58cec1
  4. _logits helper · level 1 · ran · honoured contract · 07b9c52dacc680da
  5. add_padding helper · level 0 · unverified · 8c1523b01e909dd1
  6. add_sep helper · level 0 · unverified · cece4bf90fbeb059
  7. scr helper · level 0 · unverified · afecba689fd4060e
  8. set_dropout helper · level 0 · unverified · 0bce0b5f7ae79bb2
  9. masked_log_probs helper · level 0 · unverified · 31acb1a80333fdcf
  10. shift_targets helper · level 1 · ran · violated contract · 25f478f57e667b2e
  11. binary_log_probs helper · level 1 · ran; the contract check could not run (RAISES) · 0048e4b5f0698a9b
  12. multiclass_log_probs helper · level 0 · unverified · 93f9333355fbe880
  13. es_sentiment helper · level 0 · unverified · 6b3241557810cee9
  14. gather_log_probs helper · level 1 · ran · our draft was wrong · 4930284ea4b67452
  15. mask_hf_labels helper · level 1 · ran · our draft was wrong · a559d8be7541e989
  16. masked_mean helper · level 1 · ran; the contract check could not run (RAISES) · e078eeed20f03838

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2206.06520") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Dialogue GenerationFact CheckingLanguage ModelingLanguage ModellingModel EditingQuestion AnsweringRetrievalmodel

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: SERAC

BASESERACTest

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