SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.01185 · 2026

Token-level Data Selection for Safe LLM Fine-tuning

Jun Zhang, Zijian Li, Yanping Li, Zhening Liu, Zehong Lin

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 0 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/2603.01185.json · badge: /api/ran/2603.01185.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
Polly-LYP/TOSS community
Papers with Code archive
3 ran · 0 no recorded run
FunctionStatusWhere it lives
GPTLMLoss Ran
ran on a synthesized input
Polly-LYP/TOSS/train/seal/trainer/sft_selector_trainer.py
pointer only (licence: NONE) · get_code("3c6b181ad0e31a95")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Polly-LYP/TOSS 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.

SFTSelectorTrainer Ran
ran on a synthesized input · constructed an object; no result was computed
Polly-LYP/TOSS/train/seal/trainer/sft_selector_trainer.py
pointer only (licence: NONE) · get_code("9dd571d5082c256f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Polly-LYP/TOSS 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.

batch_GPTLMLoss Ran
ran on a synthesized input
Polly-LYP/TOSS/train/seal/trainer/sft_selector_trainer.py
pointer only (licence: NONE) · get_code("ba6d9afed1cee850")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Polly-LYP/TOSS 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.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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.

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

Fine-tuning large language models (LLMs) on custom datasets has become a standard approach for adapting these models to specific domains and applications. However, recent studies have shown that such fine-tuning can lead to significant degradation in the model's safety. Existing defense methods operate at the sample level and often suffer from an unsatisfactory trade-off between safety and utility. To address this limitation, we perform a systematic token-level diagnosis of safety degradation during fine-tuning. Based on this, we propose token-level data selection for safe LLM fine-tuning (TOSS), a novel framework that quantifies the safety risk of each token by measuring the loss difference between a safety-degraded model and a utility-oriented model. This token-level granularity enables accurate identification and removal of unsafe tokens, thereby preserving valuable task-specific information. In addition, we introduce a progressive refinement strategy, TOSS-Pro, which iteratively enhances the safety-degraded model's ability to identify unsafe tokens. Extensive experiments demonstrate that our approach robustly safeguards LLMs during fine-tuning while achieving superior downstream task performance, significantly outperforming existing sample-level defense methods. Our code is available at https://github.com/Polly-LYP/TOSS.

For agents

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

get_harvested_code_for_paper("2603.01185")
get_code_for_paper("2603.01185")
have("2603.01185")

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

curl https://syntology.ai/api/ran/2603.01185.json

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

[![Syntology run record](https://syntology.ai/api/ran/2603.01185.svg)](https://syntology.ai/paper/2603.01185)

Connect an agent — have() is free.