SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.09980 · 2026

Explainable LLM Unlearning Through Reasoning

Ling Chen, Xin Yu, Zhen Fang, Qizhou Wang, Shanshan Ye, Junfeng Liao

arXiv · PDF · Open in the Atlas

Code that ran

7 of 7 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; 7 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/2603.09980.json · badge: /api/ran/2603.09980.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
junfeng1212/TRU-main canonical (classifier label)
classifier basis: census
7 ran · 0 no recorded run
FunctionStatusWhere it lives
calculate_average_scores Ran
ran; our contract draft was wrong, not the code
junfeng1212/TRU-main/LaaJ/scoring.py
pointer only (licence: NOASSERTION) · get_code("53ee75f37a0a8b1b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, junfeng1212/TRU-main (NOASSERTION). 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_batch_nll Ran
ran; our contract draft was wrong, not the code
junfeng1212/TRU-main/src/trainer/utils.py
pointer only (licence: NOASSERTION) · get_code("f5fa56fd1884242d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, junfeng1212/TRU-main (NOASSERTION). 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_dpo_loss Ran
ran; our contract draft was wrong, not the code
junfeng1212/TRU-main/src/trainer/utils.py
pointer only (licence: NOASSERTION) · get_code("ef1eb32faacefd3a")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, junfeng1212/TRU-main (NOASSERTION). 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_kl_divergence Ran
ran; our contract draft was wrong, not the code
junfeng1212/TRU-main/src/trainer/utils.py
pointer only (licence: NOASSERTION) · get_code("88e453a427b81e23")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, junfeng1212/TRU-main (NOASSERTION). 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.

forgetquality Ran
ran; our contract draft was wrong, not the code
junfeng1212/TRU-main/LaaJ/oureval.py
pointer only (licence: NOASSERTION) · get_code("65cdabf8011a97f5")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, junfeng1212/TRU-main (NOASSERTION). 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.

modelutility Ran
ran; our contract draft was wrong, not the code
junfeng1212/TRU-main/LaaJ/oureval.py
pointer only (licence: NOASSERTION) · get_code("2bbd0e46601de615")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, junfeng1212/TRU-main (NOASSERTION). 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.

save_eval Ran
ran; our contract draft was wrong, not the code
junfeng1212/TRU-main/LaaJ/oureval.py
pointer only (licence: NOASSERTION) · get_code("e6facdf402c474dd")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, junfeng1212/TRU-main (NOASSERTION). 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.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 5 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
compute_batch_nll 2 other papers
2 dated earlier
2506.12618 (2025-06)
OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics
2601.03190 (2026-01)
Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning
compute_dpo_loss 2 other papers
2 dated earlier
2506.12618 (2025-06)
OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics
2601.03190 (2026-01)
Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning

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

Warning: This paper may contain examples of harmful contents by nature. LLM unlearning is essential for mitigating safety, copyright, and privacy concerns in pre-trained large language models (LLMs). Compared to preference alignment, it offers a more explicit way by removing undesirable knowledge characterized by specific unlearning datasets. In previous works, gradient ascent (GA) and its variants have shown promise for implementing unlearning, yet their untargeted nature results in unintended degradation of general capabilities, incomplete removal of knowledge, and the generation of incoherent responses, among many others. We argue that these issues stem from the absence of explicit guidance on what and how models should unlearn. To fill this gap, we introduce a novel unlearning target, reasoning-based unlearning target, which satisfies both the specified unlearning scope and the specified post-unlearning response. Building on this, we propose targeted reasoning unlearning (TRU), which leverages reasoning-based unlearning target as guidance. We employ the target using a cross-entropy supervised loss combined with a GA-based loss, enabling the model to learn reasoning ability for precise knowledge removal while preserving unrelated abilities. We evaluate TRU against strong baselines across multiple benchmarks and LLM backbones, and find that it achieves more reliable unlearning while preserving general capabilities. Moreover, TRU exhibits superior robustness under diverse attack scenarios, stemming from the reasoning ability learned through reasoningbased targets. Overall, our study establishes reasoning-augmented unlearning as a practical paradigm for reliable and explainable LLM unlearning.

For agents

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

get_harvested_code_for_paper("2603.09980")
get_code_for_paper("2603.09980")
have("2603.09980")

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

curl https://syntology.ai/api/ran/2603.09980.json

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

[![Syntology run record](https://syntology.ai/api/ran/2603.09980.svg)](https://syntology.ai/paper/2603.09980)

Connect an agent — have() is free.