SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.09785 · ICLR · 2023

Transformer-Patcher: One Mistake worth One Neuron

Jie Zhou, Yikang Shen, Wenge Rong, Zeyu Huang, Xiaofeng Zhang, Zhang Xiong

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2301.09785.json · badge: /api/ran/2301.09785.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
ZeroYuHuang/Transformer-Patcher canonical (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
zeroyuhuang/transformer-patcher marked official in Papers with Code
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
loss_func Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ZeroYuHuang/Transformer-Patcher/src/models/patch.py
pointer only (licence: NONE) · get_code("3ef32b5700dabe8c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ZeroYuHuang/Transformer-Patcher when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

top_k_loss_func Ran
ran; our contract draft was wrong, not the code
ZeroYuHuang/Transformer-Patcher/src/models/patch.py
pointer only (licence: NONE) · get_code("d8cd20d238673a86")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ZeroYuHuang/Transformer-Patcher when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ModifyLinearOutput Not yet run
unverified (harvested, no recorded run)
zeroyuhuang/transformer-patcher/src/models/patch.py
pointer only (licence: NONE) · get_code("b2149eac0c5ba35a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zeroyuhuang/transformer-patcher when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

list_split Not yet run
unverified (harvested, no recorded run)
ZeroYuHuang/Transformer-Patcher/src/models/patch.py
pointer only (licence: NONE) · get_code("8b77980c5b963ae8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ZeroYuHuang/Transformer-Patcher when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
loss_func
brick of this paper's assembly: loss
1 other paper
1 later
2409.19872 (2024-09)
Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration
top_k_loss_func
brick of this paper's assembly: loss
1 other paper
1 later
2409.19872 (2024-09)
Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large Transformer-based Pretrained Language Models (PLMs) dominate almost all Natural Language Processing (NLP) tasks. Nevertheless, they still make mistakes from time to time. For a model deployed in an industrial environment, fixing these mistakes quickly and robustly is vital to improve user experiences. Previous works formalize such problems as Model Editing (ME) and mostly focus on fixing one mistake. However, the one-mistake-fixing scenario is not an accurate abstraction of the real-world challenge. In the deployment of AI services, there are ever-emerging mistakes, and the same mistake may recur if not corrected in time. Thus a preferable solution is to rectify the mistakes as soon as they appear nonstop. Therefore, we extend the existing ME into Sequential Model Editing (SME) to help develop more practical editing methods. Our study shows that most current ME methods could yield unsatisfying results in this scenario. We then introduce Transformer-Patcher, a novel model editor that can shift the behavior of transformer-based models by simply adding and training a few neurons in the last Feed-Forward Network layer. Experimental results on both classification and generation tasks show that Transformer-Patcher can successively correct up to thousands of errors (Reliability) and generalize to their equivalent inputs (Generality) while retaining the model's accuracy on irrelevant inputs (Locality). Our method outperforms previous fine-tuning and HyperNetwork-based methods and achieves state-of-the-art performance for Sequential Model Editing (SME). The code is available at https://github.com/ZeroYuHuang/Transform er-Patcher.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2301.09785")
get_code_for_paper("2301.09785")
have("2301.09785")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2301.09785.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2301.09785.svg)](https://syntology.ai/paper/2301.09785)

Connect an agent — have() is free.