SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.26008 · 2026

FairLLaVA: Fairness-Aware Parameter-Efficient Fine-Tuning for Large Vision-Language Assistants

Mingchen Gao, Tianyu Luan, David Doermann, Xuan Gong, Mahesh Bhosale, Abdul Wasi, Shantam Srivastava, Shifa Latif

arXiv · PDF · Open in the Atlas

Code that ran

6 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (4 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 2 failures of our instrument; 5 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/2603.26008.json · badge: /api/ran/2603.26008.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
bhosalems/FairLLaVA community
Papers with Code archive
6 ran · 5 no recorded run
FunctionStatusWhere it lives
CLUBForCategorical Ran
ran on a synthesized input · constructed an object; no result was computed
bhosalems/FairLLaVA/llava/model/language_model/llava_llama.py
pointer only (licence: NOASSERTION) · get_code("f432af9c22e8eedd")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, bhosalems/FairLLaVA (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.

DACMLP Ran
ran on a synthesized input · constructed an object; no result was computed
bhosalems/FairLLaVA/llava/model/language_model/llava_llama.py
pointer only (licence: NOASSERTION) · get_code("3b52dae02977a911")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, bhosalems/FairLLaVA (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.

DACQKV Ran
ran on a synthesized input · constructed an object; no result was computed
bhosalems/FairLLaVA/llava/model/language_model/llava_llama.py
pointer only (licence: NOASSERTION) · get_code("7c8020445edac25e")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, bhosalems/FairLLaVA (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.

GradientReversalLayer Ran
ran on a synthesized input · constructed an object; no result was computed
bhosalems/FairLLaVA/llava/model/language_model/llava_llama.py
pointer only (licence: NOASSERTION) · get_code("b4240bd567cf9949")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, bhosalems/FairLLaVA (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.

class_balanced_weights Ran
ran; our contract draft was wrong, not the code
bhosalems/FairLLaVA/llava/model/language_model/llava_llama.py
pointer only (licence: NOASSERTION) · get_code("7908703227d71533")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, bhosalems/FairLLaVA (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.

focal_loss Ran
ran; our contract draft was wrong, not the code
bhosalems/FairLLaVA/llava/model/language_model/llava_llama.py
pointer only (licence: NOASSERTION) · get_code("c48f90c323496675")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, bhosalems/FairLLaVA (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.

LlavaLlamaForCausalLM Not yet run
unverified (harvested, no recorded run)
bhosalems/FairLLaVA/llava/model/language_model/llava_llama.py
pointer only (licence: NOASSERTION) · get_code("6ea78811a0c7e746")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, bhosalems/FairLLaVA (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. No invocation recorded.

LlavaLlamaModel Not yet run
unverified (harvested, no recorded run)
bhosalems/FairLLaVA/llava/model/language_model/llava_llama.py
pointer only (licence: NOASSERTION) · get_code("428a7e6d4dcf364f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, bhosalems/FairLLaVA (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. No invocation recorded.

LlavaMetaForCausalLM Not yet run
unverified (harvested, no recorded run)
bhosalems/FairLLaVA/llava/model/language_model/llava_llama.py
pointer only (licence: NOASSERTION) · get_code("d7d5e9bc6f9033f1")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, bhosalems/FairLLaVA (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. No invocation recorded.

LlavaMetaModel Not yet run
unverified (harvested, no recorded run)
bhosalems/FairLLaVA/llava/model/language_model/llava_llama.py
pointer only (licence: NOASSERTION) · get_code("f5d8fe80c9e26fd1")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, bhosalems/FairLLaVA (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. No invocation recorded.

build_vision_tower Not yet run
unverified (harvested, no recorded run)
bhosalems/FairLLaVA/llava/model/language_model/llava_llama.py
pointer only (licence: NOASSERTION) · get_code("29b09ab62f286cf5")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, bhosalems/FairLLaVA (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. No invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 0 later) and 10 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
LlavaLlamaModel
brick of this paper's assembly: helper
13 other papers
11 dated earlier, 2 the same month · 3 only as an assembly brick
2304.08485 (2023-04)
Visual Instruction Tuning
2404.05673 (2024-04)
CoReS: Orchestrating the Dance of Reasoning and Segmentation
2405.14974 (2024-05)
LOVA 3 : Learning to Visual Question Answering, Asking and Assessment
and 10 more not named here

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

While powerful in image-conditioned generation, multimodal large language models (MLLMs) can display uneven performance across demographic groups, highlighting fairness risks. In safety-critical clinical settings, such disparities risk producing unequal diagnostic narratives and eroding trust in AI-assisted decision-making. While fairness has been studied extensively in vision-only and languageonly models, its impact on MLLMs remains largely underexplored. To address these biases, we introduce Fair-LLaVA, a parameter-efficient fine-tuning method that mitigates group disparities in visual instruction tuning without compromising overall performance. By minimizing the mutual information between target attributes, FairLLaVA regularizes the model's representations to be demographicinvariant. The method can be incorporated as a lightweight plug-in, maintaining efficiency with low-rank adapter finetuning, and provides an architecture-agnostic approach to fair visual instruction following. Extensive experiments on large-scale chest radiology report generation and dermoscopy visual question answering benchmarks show that FairLLaVA consistently reduces inter-group disparities while improving both equity-scaled clinical performance and natural language generation quality across diverse medical imaging modalities. Code can be accessed at https://github.com/bhosalems/FairLLaVA.

For agents

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

get_harvested_code_for_paper("2603.26008")
get_code_for_paper("2603.26008")
have("2603.26008")

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

curl https://syntology.ai/api/ran/2603.26008.json

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

[![Syntology run record](https://syntology.ai/api/ran/2603.26008.svg)](https://syntology.ai/paper/2603.26008)

Connect an agent — have() is free.