SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.11844 · 2024

MEOW: MEMOry Supervised LLM Unlearning Via Inverted Facts

arXiv · PDF · Open in the Atlas

Code that ran

8 of 11 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; 8 failures of our instrument; 3 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/2409.11844.json · badge: /api/ran/2409.11844.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
carol-gutianle/meow canonical (classifier label)
classifier basis: census
8 ran · 3 no recorded run
FunctionStatusWhere it lives
custom_data_collator Ran
ran; our contract draft was wrong, not the code
carol-gutianle/meow/meow/dataset.py
pointer only (licence: NONE) · get_code("5985b70afc6ef2b0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, carol-gutianle/meow 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.

custom_data_collator_forget Ran
ran; our contract draft was wrong, not the code
carol-gutianle/meow/meow/dataset.py
pointer only (licence: NONE) · get_code("b3dab92b14270b57")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, carol-gutianle/meow 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.

custom_data_collator_with_indices Ran
ran; our contract draft was wrong, not the code
carol-gutianle/meow/meow/dataset.py
pointer only (licence: NONE) · get_code("0978589be4224d97")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, carol-gutianle/meow 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.

find_all_linear_names Ran
ran; our contract draft was wrong, not the code
carol-gutianle/meow/meow/tofu/finetune.py
pointer only (licence: NONE) · get_code("649fc48067a48529")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, carol-gutianle/meow 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.

get_batch_loss Ran
ran; our contract draft was wrong, not the code
carol-gutianle/meow/meow/utils.py
pointer only (licence: NONE) · get_code("442bc919060e0f2b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, carol-gutianle/meow 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.

get_forget_quality Ran
ran; our contract draft was wrong, not the code
carol-gutianle/meow/meow/tofu/aggregate.py
pointer only (licence: NONE) · get_code("c55fe02db3bba2fc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, carol-gutianle/meow 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_data_from_json Ran
ran; our contract draft was wrong, not the code
carol-gutianle/meow/memo/memo.py
pointer only (licence: NONE) · get_code("b89fc6709df8d03f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, carol-gutianle/meow 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.

main Ran
ran; our contract draft was wrong, not the code
carol-gutianle/meow/meow/tofu/aggregate.py
pointer only (licence: NONE) · get_code("956672833b0ef856")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, carol-gutianle/meow 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.

get_model_identifiers_from_yaml Not yet run
unverified (harvested, no recorded run)
carol-gutianle/meow/meow/utils.py
pointer only (licence: NONE) · get_code("644003af682c4c68")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, carol-gutianle/meow 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_model_utility Not yet run
unverified (harvested, no recorded run)
carol-gutianle/meow/meow/utils.py
pointer only (licence: NONE) · get_code("a29a4722ab1dd2d8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, carol-gutianle/meow 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_model_utility Not yet run
unverified (harvested, no recorded run)
carol-gutianle/meow/meow/tofu/aggregate.py
pointer only (licence: NONE) · get_code("fc4739c113213ace")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, carol-gutianle/meow 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 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 3 later) and 6 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
find_all_linear_names 22 other papers
14 dated earlier, 7 later, 1 same year, order not determinable
2308.09936 (2023-08)
BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions
2310.13023 (2023-10)
GraphGPT: Graph Instruction Tuning for Large Language Models
2311.13194 (2023-11)
Towards Improving Document Understanding: An Exploration on Text-Grounding via MLLMs
and 19 more not named here
custom_data_collator 5 other papers
2 dated earlier, 3 later
2401.06121 (2024-01)
TOFU: A Task of Fictitious Unlearning for LLMs
2407.16997 (2024-07)
Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective
2410.15153 (2024-10)
Evaluating Deep Unlearning in Large Language Models
and 2 more not named here
get_batch_loss 4 other papers
1 dated earlier, 3 later
2307.13702 (2023-07)
Measuring Faithfulness in Chain-of-Thought Reasoning
2502.14829 (2025-02)
Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps
2506.01339 (2025-06)
Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
and 1 more not named here
get_forget_quality 1 other paper
1 dated earlier
2401.06121 (2024-01)
TOFU: A Task of Fictitious Unlearning for LLMs
get_model_utility 1 other paper
1 dated earlier
2401.06121 (2024-01)
TOFU: A Task of Fictitious Unlearning for LLMs

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 Language Models (LLMs) can memorize sensitive information, raising concerns about potential misuse. LLM Unlearning, a post-hoc approach to remove this information from trained LLMs, offers a promising solution to mitigate these risks. However, previous practices face three key challenges: 1. Utility: successful unlearning often causes catastrophic collapse on unrelated tasks. 2. Efficiency: many methods either involve adding similarly sized models, which slows down unlearning or inference, or require retain data that are difficult to obtain. 3. Robustness: even effective methods may still leak data via extraction techniques. To address these challenges, we propose MEOW, a simple yet effective gradient descent-based unlearning method. Specifically, we use an offline LLM to generate a set of inverted facts. Then, we design a new metric, MEMO, to quantify memorization in LLMs. Finally, based on the signals provided by MEMO, we select the most appropriate set of inverted facts and finetune the model based on them. We evaluate MEOW on the commonly used unlearn benchmark, ToFU, with Llama2-7B-Chat and Phi-1.5B, and test it on both NLU and NLG tasks. Results demonstrate significant improvement of MEOW in forget quality without substantial loss in model utility. Meanwhile, MEOW does not exhibit significant degradation in NLU or NLG capabilities, and there is even a slight improvement in NLU performance.

For agents

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

get_harvested_code_for_paper("2409.11844")
get_code_for_paper("2409.11844")
have("2409.11844")

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

curl https://syntology.ai/api/ran/2409.11844.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.11844.svg)](https://syntology.ai/paper/2409.11844)

Connect an agent — have() is free.