Methods › General › Meta-Learning Algorithms › MEND
MODEL EDITOR NETWORKS WITH GRADIENT DECOMPOSITION
MEND
Introduced by Eric Mitchell et al. in Fast Model Editing at Scale
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
The archive carries no description for this method.
In Syntology about another paper, arXiv:2609.39182: no code under this exact name (no_code; paper_only). About another paper: this answer is about arXiv:2609.39182, while the archive credits arXiv:2110.11309, so it does not say whether this method has code.
From the lookup's note on this name: The same name also belongs to “Model Editor Networks with Gradient Decomposition (MEND)”, a method in the paper “Fast Model Editing at Scale” (arXiv:2110.11309, 603 citations), which the lookup finds cited far more than the paper this answer is about (citations not recorded), so this answer may be about a different sense of the name. For arXiv:2110.11309: its page on this site · ask the lookup about it.
Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.
- Model Editor Networks with Gradient Decomposition (MEND) · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Model Editor Networks with Gradient Decomposition (MEND)')
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.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 11 · with a code link: 7 · where Syntology ran a sample: 4 (4 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (4 of 11 tagged: 4 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 11 of 11, 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.
-
PropMEND: Hypernetworks for Knowledge Propagation in LLMs 10 Jun 2025 · 1 repository · arXiv:2506.08920
-
Your Language Model May Think Too Rigidly: Achieving Reasoning Consistency with Symmetry-Enhanced Training 25 Feb 2025 · 0 repositories · arXiv:2502.17800
-
Declarative Knowledge Distillation from Large Language Models for Visual Question Answering Datasets 12 Oct 2024 · 1 repository · arXiv:2410.09428
-
From Text to Emoji: How PEFT-Driven Personality Manipulation Unleashes the Emoji Potential in LLMs 16 Sep 2024 · 0 repositories · arXiv:2409.10245
-
Transformers Can Do Arithmetic with the Right Embeddings 27 May 2024 · 1 repository · arXiv:2405.17399Syntology official (archive's flag): 12 ran · 12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 4 honoured, 1 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 13 harvested samples)
-
VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark 12 Mar 2024 · 1 repository · arXiv:2403.07350Syntology official (archive's flag): 9 ran · 22 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 13 where Syntology's instrument failed) · 3 unverified (of 25 harvested samples) · 5 pointer-only (licence)
-
MEND: Meta dEmonstratioN Distillation for Efficient and Effective In-Context Learning 11 Mar 2024 · 1 repository · arXiv:2403.06914Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
A Comprehensive Study of Knowledge Editing for Large Language Models 2 Jan 2024 · 2 repositories · arXiv:2401.01286
-
Mending of Spatio-Temporal Dependencies in Block Adjacency Matrix 4 Oct 2023 · 0 repositories · arXiv:2310.02606
-
An Analysis of Dialogue Repair in Virtual Voice Assistants 13 Jul 2023 · 0 repositories · arXiv:2307.07076
-
Fast Model Editing at Scale 21 Oct 2021 · 3 repositories · arXiv:2110.11309Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
Tasks archive 2025-07-28
18 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
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
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