SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.11078 · 2024

Model Editing by Standard Fine-Tuning

arXiv · PDF · Open in the Atlas

Code that ran

6 of 16 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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 10 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/2402.11078.json · badge: /api/ran/2402.11078.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
au-revoir/model-editing-ft canonical (classifier label)
classifier basis: census
6 ran · 10 no recorded run
FunctionStatusWhere it lives
calculate_accuracy Ran
ran, honoured the contract we drafted
au-revoir/model-editing-ft/eval_counterfact.py
pointer only (licence: NONE) · get_code("22d5862d2be6ea55")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, au-revoir/model-editing-ft 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.

calculate_accuracy Ran
ran, honoured the contract we drafted
au-revoir/model-editing-ft/eval_wiki_recent.py
pointer only (licence: NONE) · get_code("7d11acc3973989ae")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, au-revoir/model-editing-ft 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.

calculate_accuracy Ran
ran, honoured the contract we drafted
au-revoir/model-editing-ft/eval_zsre.py
pointer only (licence: NONE) · get_code("6eac6ac95f073c9b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, au-revoir/model-editing-ft 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.

convert_to_scalar Ran
ran; our contract draft was wrong, not the code
au-revoir/model-editing-ft/trl/core.py
pointer only (licence: NONE) · get_code("8483cffb5dea03d2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, au-revoir/model-editing-ft 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.

load_result_json_files Ran
ran; our contract draft was wrong, not the code
au-revoir/model-editing-ft/summarize_consistency_fluency.py
pointer only (licence: NONE) · get_code("7ef6c77fb3c41271")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, au-revoir/model-editing-ft 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.

stack_dicts Ran
ran; our contract draft was wrong, not the code
au-revoir/model-editing-ft/trl/core.py
pointer only (licence: NONE) · get_code("7dc16cc69c54c94d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, au-revoir/model-editing-ft 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.

compute_n_gram_entropy Not yet run
unverified (harvested, no recorded run)
au-revoir/model-editing-ft/calculate_ge_rs.py
pointer only (licence: NONE) · get_code("4b7820536046b5d3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, au-revoir/model-editing-ft 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.

flatten_dict Not yet run
unverified (harvested, no recorded run)
au-revoir/model-editing-ft/trl/core.py
pointer only (licence: NONE) · get_code("1782ce5551146615")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, au-revoir/model-editing-ft 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.

generate_fast Not yet run
unverified (harvested, no recorded run)
au-revoir/model-editing-ft/generate.py
pointer only (licence: NONE) · get_code("7f36cf283f994f81")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, au-revoir/model-editing-ft 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.

get_peft_config Not yet run
unverified (harvested, no recorded run)
au-revoir/model-editing-ft/config.py
pointer only (licence: NONE) · get_code("68ccd7601bf63c02")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, au-revoir/model-editing-ft 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.

get_tfidf_vectorizer Not yet run
unverified (harvested, no recorded run)
au-revoir/model-editing-ft/tfidf_stats.py
pointer only (licence: NONE) · get_code("d74c89166816770f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, au-revoir/model-editing-ft 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.

initialize_training_args Not yet run
unverified (harvested, no recorded run)
au-revoir/model-editing-ft/config.py
pointer only (licence: NONE) · get_code("a4c1dac0b23a543f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, au-revoir/model-editing-ft 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.

n_gram_entropy Not yet run
unverified (harvested, no recorded run)
au-revoir/model-editing-ft/calculate_ge_rs.py
pointer only (licence: NONE) · get_code("14ad65e85245ae37")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, au-revoir/model-editing-ft 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.

test_batch_prediction Not yet run
unverified (harvested, no recorded run)
au-revoir/model-editing-ft/eval_counterfact.py
pointer only (licence: NONE) · get_code("a2f59fd52a85ae0f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, au-revoir/model-editing-ft 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.

test_batch_prediction Not yet run
unverified (harvested, no recorded run)
au-revoir/model-editing-ft/eval_wiki_recent.py
pointer only (licence: NONE) · get_code("ffd39e3f4599fac9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, au-revoir/model-editing-ft 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.

test_batch_prediction_acc Not yet run
unverified (harvested, no recorded run)
au-revoir/model-editing-ft/eval_wiki_recent.py
pointer only (licence: NONE) · get_code("995ae50aa2cb1d90")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, au-revoir/model-editing-ft 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 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 4 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 4 later) and 12 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
convert_to_scalar 2 other papers
2 later
2403.06754 (2024-03)
ALaRM: Align Language Models via Hierarchical Rewards Modeling
2501.06911 (2025-01)
Risk-Averse Fine-tuning of Large Language Models
flatten_dict 2 other papers
2 later
2403.06754 (2024-03)
ALaRM: Align Language Models via Hierarchical Rewards Modeling
2501.06911 (2025-01)
Risk-Averse Fine-tuning of Large Language Models
stack_dicts 2 other papers
2 later
2403.06754 (2024-03)
ALaRM: Align Language Models via Hierarchical Rewards Modeling
2501.06911 (2025-01)
Risk-Averse Fine-tuning of Large Language Models
compute_n_gram_entropy 1 other paper
1 later
2507.08427 (2025-07)
ChainEdit: Propagating Ripple Effects in LLM Knowledge Editing through Logical Rule-Guided Chains

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

Standard fine-tuning is considered not as effective as specialized methods for model editing due to its comparatively poor performance. However, it is simple, agnostic to the architectural details of the model being edited, and able to leverage advances in standard training techniques with no additional work (e.g., black-box PEFT for computational efficiency), making it an appealing choice for a model editor. In this work, we show that standard fine-tuning alone can yield competitive model editing performance with two minor modifications. First, we optimize the conditional likelihood rather than the full likelihood. Second, in addition to the typical practice of training on randomly paraphrased edit prompts to encourage generalization, we also train on random or similar unedited facts to encourage locality. Our experiments on the ZsRE and CounterFact datasets demonstrate that these simple modifications allow standard fine-tuning to match or outperform highly specialized editors in terms of edit score.

For agents

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

get_harvested_code_for_paper("2402.11078")
get_code_for_paper("2402.11078")
have("2402.11078")

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

curl https://syntology.ai/api/ran/2402.11078.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.11078.svg)](https://syntology.ai/paper/2402.11078)

Connect an agent — have() is free.