SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2609.02496 · September 2026

Debias-SparseGPT: Bias-Aware Pruning for Large Language Models

Irina Proskurina, Guillaume Metzler, Julien Velcin, Antoine Gourru

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 1 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/2609.02496.json · badge: /api/ran/2609.02496.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
upunaprosk/debias-llm-compressor canonical (classifier label)
classifier basis: census
5 ran · 1 no recorded run
FunctionStatusWhere it lives
accumulate_hessian Ran
ran; our contract draft was wrong, not the code
upunaprosk/debias-llm-compressor/debias_sparsegpt_ss/modifiers/pruning/sparsegpt/sgpt_sparsify.orig.py
pointer only (licence: NONE) · get_code("01d8a76e172ac023")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, upunaprosk/debias-llm-compressor 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.

accumulate_hessian Ran
ran; our contract draft was wrong, not the code
upunaprosk/debias-llm-compressor/debias_sparsegpt_ss/modifiers/pruning/sparsegpt/sgpt_sparsify.py
pointer only (licence: NONE) · get_code("d64b262d8c2b1c99")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, upunaprosk/debias-llm-compressor 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.

accumulate_hessian Ran
ran; our contract draft was wrong, not the code
upunaprosk/debias-llm-compressor/debias_sparsegpt_ultrachat/modifiers/pruning/sparsegpt/sgpt_sparsify.py
pointer only (licence: NONE) · get_code("d1b0981b665b322e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, upunaprosk/debias-llm-compressor 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.

make_empty_hessian Ran
ran, honoured the contract we drafted
upunaprosk/debias-llm-compressor/debias_sparsegpt_ss/modifiers/pruning/sparsegpt/sgpt_sparsify.orig.py
pointer only (licence: NONE) · get_code("b62f05a57b80c9ce")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, upunaprosk/debias-llm-compressor 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.

sparsify_weight Ran
ran; our contract draft was wrong, not the code
upunaprosk/debias-llm-compressor/debias_sparsegpt_ss/modifiers/pruning/sparsegpt/sgpt_sparsify.orig.py
pointer only (licence: NONE) · get_code("98d65f8250e03f6c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, upunaprosk/debias-llm-compressor 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.

format_calibration_data Not yet run
unverified (harvested, no recorded run)
upunaprosk/debias-llm-compressor/debias_sparsegpt_ss/datasets/utils.orig.py
pointer only (licence: NONE) · get_code("ab0b02750e52f721")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, upunaprosk/debias-llm-compressor 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 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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 6 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

Model compression techniques such as pruning and quantization facilitate the efficient deployment and acceleration of Large Language Models (LLMs). However, recent studies show that weight sparsification methods, such as SparseGPT, can amplify existing biases in models, with outputs varying significantly depending on persona cues in the prompt. In this paper, we introduce Debias-SparseGPT, a post-training pruning method incorporating representational debiasing using a second-order term defined over demographically contrasting inputs. We perform empirical validation of our method over a wide range of generative LLMs. Across models and sparsity regimes (25%, 50%, and structured 2:4 sparsity), Debias-SparseGPT consistently reduces pruning-induced bias compared to SparseGPT while preserving model perplexity and zero-shot accuracy. Under the most restrictive 2:4 structured sparsity pattern, which most aggressively degrades model quality, augmenting the calibration set with long-context, content-rich examples further improves both downstream performance and fairness. Overall, Debias-SparseGPT advances the bias-performance trade-off while preserving the computational efficiency of sparse models.

For agents

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

get_harvested_code_for_paper("2609.02496")
get_code_for_paper("2609.02496")
have("2609.02496")

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

curl https://syntology.ai/api/ran/2609.02496.json

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

[![Syntology run record](https://syntology.ai/api/ran/2609.02496.svg)](https://syntology.ai/paper/2609.02496)

Connect an agent — have() is free.