Tsui-Wei Weng, Chung-En Sun, Yongce Li
1 of 1 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; 1 failure of our instrument; 0 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/2503.21730.json · badge: /api/ran/2503.21730.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.
| Repository | Role | Ran |
|---|---|---|
| Trustworthy-ML-Lab/effective_skill_unlearning | community Papers with Code archive |
1 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| get_neuron_mean_std_adjust_info | Ran ran; our contract draft was wrong, not the code |
Trustworthy-ML-Lab/effective_skill_unlearning/get_adjust_info.py pointer only (licence: NONE) · get_code("d14b3a58617f1b90") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, Trustworthy-ML-Lab/effective_skill_unlearning 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. |
Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 1 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.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Large language Models (LLMs) have demonstrated remarkable skills across various domains. Understanding the mechanisms behind their abilities and implementing controls over them is becoming increasingly important for developing better models. In this paper, we focus on skill unlearning in LLMs, specifically unlearning a particular skill while retaining their overall capabilities. We introduce two lightweight, training-free machine skill unlearning techniques for LLMs. First, we observe that the pre-activation distribution of neurons in each Feed-Forward Layer (FFL) differs when the model demonstrates different skills. Additionally, we find that queries triggering the same skill cluster within the FFL key space and can be separated from other queries using a hypercube. Based on these observations, we propose two lightweight, training-free skill unlearning methods via intervention and abstention respectively: Neuron Adjust and Key Space Detection. We evaluate our methods on unlearning math-solving, Python-coding, and comprehension skills across seven different languages. The results demonstrate their strong unlearning capabilities for the designated skills. Specifically, Key Space Detection achieves over 80% relative performance drop on the forgetting skill and less than 10% relative performance drop on other skills and the model's general knowledge (MMLU) for most unlearning tasks. 1 (I) Efficiency (II) Performance (III) Scalability Method: Does not require training No Inference time cost High quality unlearning Maintain model overall capability Applicable to large models Retrain from scratch No Yes Yes Yes No Fine-tuning based unlearning No Yes Yes No Yes In-context unlearning Yes Yes No Yes Yes Selective Pruning Yes Yes Yes No Yes Neuron Adjust (Ours) Yes O(1) Yes Partial Yes Key Space Detection (Ours) Yes O(1) Yes Yes Yes Table 1: Comparison of our method against existing machine unlearning methods, including retraining, fine-tuning based methods, in-context unlearning, and a prune-based unlearning method Selective Pruning.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2503.21730")
get_code_for_paper("2503.21730")
have("2503.21730")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2503.21730.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2503.21730)
Connect an agent — have() is free.