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 ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2206.06520")

Code

Syntology Ran 6 of 14 code samples harvested from 1 repository linked to this paper; 8 have no recorded run. Of those that ran: 1 ran · violated contract; 2 ran · our draft was wrong; 2 ran · fixture could not drive it; 1 ran with no contract checked.

By repository: community (archive-listed): 14 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

eric-mitchell/serac mentioned on GitHubpytorch 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; 0 honoured the contract we drafted; 8 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · violated contract
2ran · our draft was wrong
2ran · fixture could not drive it
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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

EditableModel eric-mitchell/serac/algs/rep.py community (archive-listed) ran MIT (permissive) · 1946baf07d58cec1 · report
binary_log_probs eric-mitchell/serac/algs/rep.py community (archive-listed) ran · fixture could not drive it fingerprinted MIT (permissive) · 0048e4b5f0698a9b · report
gather_log_probs eric-mitchell/serac/algs/rep.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 4930284ea4b67452 · report
mask_hf_labels eric-mitchell/serac/algs/rep.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · a559d8be7541e989 · report
masked_mean eric-mitchell/serac/algs/rep.py community (archive-listed) ran · fixture could not drive it MIT (permissive) · e078eeed20f03838 · report
shift_targets eric-mitchell/serac/algs/rep.py community (archive-listed) ran · violated contract MIT (permissive) · 25f478f57e667b2e · report
BertClassifier eric-mitchell/serac/algs/rep.py community (archive-listed) unverified MIT (permissive) · 16b1893e8ab378bf · report
REP eric-mitchell/serac/algs/rep.py community (archive-listed) unverified MIT (permissive) · 8c62b93f788354a1 · report
add_padding eric-mitchell/serac/algs/rep.py community (archive-listed) unverified MIT (permissive) · 8c1523b01e909dd1 · report
add_sep eric-mitchell/serac/algs/rep.py community (archive-listed) unverified MIT (permissive) · cece4bf90fbeb059 · report
es_sentiment eric-mitchell/serac/algs/rep.py community (archive-listed) unverified MIT (permissive) · 6b3241557810cee9 · report
masked_log_probs eric-mitchell/serac/algs/rep.py community (archive-listed) unverified MIT (permissive) · 31acb1a80333fdcf · report
multiclass_log_probs eric-mitchell/serac/algs/rep.py community (archive-listed) unverified MIT (permissive) · 93f9333355fbe880 · report
scr eric-mitchell/serac/algs/rep.py community (archive-listed) unverified MIT (permissive) · afecba689fd4060e · report

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