SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.02718 · 2024

"Yes, My LoRD." Guiding Language Model Extraction with Locality Reinforced Distillation

arXiv · PDF · Open in the Atlas

Code that ran

6 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; 6 failures of our instrument; 1 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/2409.02718.json · badge: /api/ran/2409.02718.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
liangzid/alignmentextraction canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
liangzid/lord-mea canonical (classifier label)
classifier basis: census
1 ran · 1 no recorded run
FunctionStatusWhere it lives
bleu_count Ran
ran; our contract draft was wrong, not the code
liangzid/alignmentextraction/bleu4.py
pointer only (licence: NONE) · get_code("622878101d35577d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, liangzid/alignmentextraction 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.

corpus_bleu Ran
ran; our contract draft was wrong, not the code
liangzid/alignmentextraction/bleu4.py
pointer only (licence: NONE) · get_code("11aff40704a6d93e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, liangzid/alignmentextraction 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.

eval_code Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
liangzid/alignmentextraction/code_process.py
pointer only (licence: NONE) · get_code("d19477d96c073c77")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, liangzid/alignmentextraction 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.

eval_siQA Ran
ran; our contract draft was wrong, not the code
liangzid/alignmentextraction/common_task_process.py
pointer only (licence: NONE) · get_code("9b68d7c8c2502e0c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, liangzid/alignmentextraction 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.

formatting_func Ran
ran; our contract draft was wrong, not the code
liangzid/alignmentextraction/supervised_finetuning.py
pointer only (licence: NONE) · get_code("ac86eca2846149a7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, liangzid/alignmentextraction 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.

random_take Ran
ran; our contract draft was wrong, not the code
liangzid/lord-mea/train_pod4_lord_II.py
pointer only (licence: NONE) · get_code("9d95cead689f7ef6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, liangzid/lord-mea 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.

reinforce_train_one_period Not yet run
unverified (harvested, no recorded run)
liangzid/lord-mea/lord_reinforce_train.py
pointer only (licence: NONE) · get_code("3f1d6e8a3a90c43c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, liangzid/lord-mea 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 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
bleu_count 1 other paper
1 dated earlier
1905.12926 (2019-05)
Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent Representation
corpus_bleu 1 other paper
1 dated earlier
1905.12926 (2019-05)
Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent Representation

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

Model extraction attacks (MEAs) on large language models (LLMs) have received increasing attention in recent research. However, existing attack methods typically adapt the extraction strategies originally developed for deep neural networks (DNNs). They neglect the underlying inconsistency between the training tasks of MEA and LLM alignment, leading to suboptimal attack performance. To tackle this issue, we propose Locality Reinforced Distillation (LoRD), a novel model extraction algorithm specifically designed for LLMs. In particular, LoRD employs a newly defined policy-gradient-style training task that utilizes the responses of victim model as the signal to guide the crafting of preference for the local model. Theoretical analyses demonstrate that I) The convergence procedure of LoRD in model extraction is consistent with the alignment procedure of LLMs, and II) LoRD can reduce query complexity while mitigating watermark protection through our exploration-based stealing. Extensive experiments validate the superiority of our method in extracting various state-of-the-art commercial LLMs. Our code is available at: https://github.com/liangzid/LoRD-MEA .

For agents

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

get_harvested_code_for_paper("2409.02718")
get_code_for_paper("2409.02718")
have("2409.02718")

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

curl https://syntology.ai/api/ran/2409.02718.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.02718.svg)](https://syntology.ai/paper/2409.02718)

Connect an agent — have() is free.