SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.18346 · 2024

Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective

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 (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; 3 failures 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/2403.18346.json · badge: /api/ran/2403.18346.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
opencausalab/more canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
convert_options Ran
ran; our contract draft was wrong, not the code
opencausalab/more/utils/utils.py
code served (permissive licence) · get_code("e7435ea75879d451")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function convert_options takes a list of options (strings)
# and formats them with letters (A, B, C, etc.)
# It iterates through options, formats each one, and joins them with newlines

options = [
    "First option",
    "Second option",
    "Third option"
]

ARGS = {
    "options": options
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
encode_image Ran
ran; our contract draft was wrong, not the code
opencausalab/more/utils/utils.py
code served (permissive licence) · get_code("5366edd7a38c7f65")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import base64
import io
from PIL import Image
import numpy as np

# Create a small test image as a PIL Image object
image_array = np.random.randint(0, 256, (10, 10, 3), dtype=np.uint8)
pil_image = Image.fromarray(image_array)

# Test with a PIL Image object (non-string case)
ARGS = {
    'image_path': pil_image
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
prompt_answer Ran
ran; our contract draft was wrong, not the code
opencausalab/more/utils/utils.py
code served (permissive licence) · get_code("49ed499a6a37a10e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Analyzing the function:
# - c_task: string parameter that is compared to 'open_ended'
# - E_INST: string parameter that is conditionally included in f-string

ARGS = {
    'c_task': 'open_ended',
    'E_INST': '[INST] '
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

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, 3 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 0 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
convert_options 1 other paper
1 same year, order not determinable
2024.findings-emnlp.960 (2024 (year only))
Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective
encode_image 1 other paper
1 same year, order not determinable
2024.findings-emnlp.960 (2024 (year only))
Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective
prompt_answer 1 other paper
1 same year, order not determinable
2024.findings-emnlp.960 (2024 (year only))
Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective

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

Recent advancements in Large Language Models (LLMs) have facilitated the development of Multimodal LLMs (MLLMs). Despite their impressive capabilities, MLLMs often suffer from over-reliance on unimodal biases (e.g., language bias and vision bias), leading to incorrect answers or hallucinations in complex multimodal tasks. To investigate this issue, we propose a causal framework to interpret the biases in Visual Question Answering (VQA) problems. Within this framework, we conduct an in-depth causal analysis to assess the causal effect of these biases on MLLM predictions. Based on the analysis, we introduce 1) a novel MORE dataset with 12,000 challenging VQA instances requiring multi-hop reasoning and overcoming unimodal biases. 2) a causality-enhanced agent framework CAVE that guides models to comprehensively integrate information from different modalities and mitigate biases. Our experiments show that MLLMs perform poorly on MORE, indicating strong unimodal biases and limited semantic understanding. However, when integrated with our CAVE, promising improvements in reasoning and bias mitigation can be seen. These findings provide important insights for the development of more robust MLLMs and contribute to the broader goal of advancing multimodal AI systems capable of deeper understanding and reasoning. Our project page is at https://github.com/OpenCausaLab/MORE.

For agents

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

get_harvested_code_for_paper("2403.18346")
get_code_for_paper("2403.18346")
have("2403.18346")

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

curl https://syntology.ai/api/ran/2403.18346.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.18346.svg)](https://syntology.ai/paper/2403.18346)

Connect an agent — have() is free.