Papers › TOFU: A Task of Fictitious Unlearning for LLMs

TOFU: A Task of Fictitious Unlearning for LLMs

11 Jan 2024arXiv:2401.06121archive 2025-07-28

Pratyush Maini, Zhili Feng, Avi Schwarzschild, Zachary C. Lipton, J. Zico Kolter

Large language models trained on massive corpora of data from the web can memorize and reproduce sensitive or private data raising both legal and ethical concerns. Unlearning, or tuning models to forget information present in their training data, provides us with a way to protect private data after training. Although several methods exist for such unlearning, it is unclear to what extent they result in models equivalent to those where the data to be forgotten was never learned in the first place. To address this challenge, we present TOFU, a Task of Fictitious Unlearning, as a benchmark aimed at helping deepen our understanding of unlearning. We offer a dataset of 200 diverse synthetic author profiles, each consisting of 20 question-answer pairs, and a subset of these profiles called the forget set that serves as the target for unlearning. We compile a suite of metrics that work together to provide a holistic picture of unlearning efficacy. Finally, we provide a set of baseline results from existing unlearning algorithms. Importantly, none of the baselines we consider show effective unlearning motivating continued efforts to develop approaches for unlearning that effectively tune models so that they truly behave as if they were never trained on the forget data at all.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 14 code samples harvested from 2 repositories linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 14 samples from 2 repositories, 10 ran (3 with no instrument failure; 7 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 10 samples that ran has no recorded date.

locuslab/open-unlearning mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics (arXiv:2506.12618; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
locuslab/tofu mentioned on GitHubpytorchMITSyntology: 12 samples, 8 ran (5 instrument-failed) · 4 unverified report
lululu008/waterdrum mentioned on GitHubpytorchSyntology: not harvested report
mehrdadsaberi/msa_unlearning mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Model State Arithmetic for Machine Unlearning (arXiv:2506.20941; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
ucsb-nlp-chang/uld mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
wrh14/deep_unlearning mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Evaluating Deep Unlearning in Large Language Models (arXiv:2410.15153; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

14 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
6ran · our draft was wrong
1ran; the contract check could not run
1ran
4unverified

Licence: 5 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. For 5 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

locuslab/tofu community (archive-listed) 12 samples, 8 ran (5 instrument-failed) · 4 unverified
collate_fn in 500 papers data_module.py ran · honoured contract MIT (permissive) · cdd171f20cd6f53d · report fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-24
compute_metrics in 208 papers dataloader.py ran · our draft was wrong MIT (permissive) · 88a4f13abd54a00c · report fixture: signature pred:PredObject/0/? · returned dict · level recorded 2026-09-24
custom_data_collator in 6 papers data_module.py ran · our draft was wrong MIT (permissive) · 5985b70afc6ef2b0 · report fixture: signature samples:list/1/tuple · returned tuple · level recorded 2026-09-24
custom_data_collator_forget in 6 papers dataloader.py ran; the contract check could not run (RAISES) MIT (permissive) · e951dedc21c69ac1 · report fixture: signature samples:list/1/tuple · returned list · level recorded 2026-09-24
find_all_linear_names in 50 papers finetune.py ran · our draft was wrong MIT (permissive) · 649fc48067a48529 · report fixture: signature model:callable/0/? · returned list · level recorded, date not recorded
get_forget_quality in 7 papers aggregate_eval_stat.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · c55fe02db3bba2fc · report fixture: signature unlearn_result:dict/0/?, retain_result:dict/0/? · returned dict · level recorded 2026-09-24
get_loss in 107 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 4 buckets, one shared input per bucket
dataloader.py ran MIT (permissive) · 650d5f6bfcd7d9bb · report fixture: signature output:Tensor/3/float, labels:Tensor/2/int · returned Tensor · level recorded 2026-09-24
get_total_len in 6 papers utils.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 6c542acea5aa211c · report fixture: signature name:str/0/str, forget_rate:str/0/str · returned int · level recorded 2026-09-24
convert_raw_data_to_model_format in 10 papers data_module.py unverified MIT (permissive) here; the stored copy is pointer only · 7dec325d088c0b76 · report
get_model_identifiers_from_yaml in 12 papers utils.py unverified MIT (permissive) here; the stored copy is pointer only · 06448b0513272463 · report
get_model_utility in 5 papers aggregate_eval_stat.py unverified MIT (permissive) here; the stored copy is pointer only · fc4739c113213ace · report
main in 235 papers aggregate_eval_stat.py unverified MIT (permissive) · 76eaabd6bddc940d · report
ucsb-nlp-chang/uld community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
collect_expand_data uld/data/tofu.py ran · our draft was wrong MIT (permissive) · 4a7aed8249a0f503 · report fixture: signature expand_qanum:int/0/int, path:str/0/str · returned list · level recorded 2026-09-22
collect_perturb_data uld/data/tofu.py ran · our draft was wrong MIT (permissive) · 335890848a41a7ae · report fixture: signature expand_qanum:int/0/int, path:str/0/str · returned list · level recorded 2026-09-22

Datasets

Introduced by this paper, per the archive.

TOFU

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SET

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