SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.11665 · ICLR · 2025

See It from My Perspective: How Language Affects Cultural Bias in Image Understanding

Mohit Bansal, Elias Stengel-Eskin, Amith Ananthram, Kathleen Mckeown

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; 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/2406.11665.json · badge: /api/ran/2406.11665.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
amith-ananthram/see-it-from-my-perspective canonical (classifier label)
classifier basis: census
5 ran · 1 no recorded run
FunctionStatusWhere it lives
clean_generation Ran
ran; our contract draft was wrong, not the code
amith-ananthram/see-it-from-my-perspective/utils.py
pointer only (licence: NONE) · get_code("db19112cf3afad4c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, amith-ananthram/see-it-from-my-perspective 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.

get_output_key Ran
ran; our contract draft was wrong, not the code
amith-ananthram/see-it-from-my-perspective/3_judge_dollarstreet_with_prometheus.py
pointer only (licence: NONE) · get_code("ff3df9199f8ff9b5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, amith-ananthram/see-it-from-my-perspective 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.

parse_selection Ran
ran, honoured the contract we drafted
amith-ananthram/see-it-from-my-perspective/2_extract_mcvqa_artelingo_selections.py
pointer only (licence: NONE) · get_code("2d9478181954b86e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, amith-ananthram/see-it-from-my-perspective 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.

prepare_inputs Ran
ran; our contract draft was wrong, not the code
amith-ananthram/see-it-from-my-perspective/3_judge_dollarstreet_with_prometheus.py
pointer only (licence: NONE) · get_code("d065eeaf46e1419c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, amith-ananthram/see-it-from-my-perspective 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.

prompt_collator Ran
ran; our contract draft was wrong, not the code
amith-ananthram/see-it-from-my-perspective/1_run_vlm_cultural_bias_inference.py
pointer only (licence: NONE) · get_code("f39913d7cb0b3a04")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, amith-ananthram/see-it-from-my-perspective 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.

load_to_process Not yet run
unverified (harvested, no recorded run)
amith-ananthram/see-it-from-my-perspective/3_judge_dollarstreet_with_prometheus.py
pointer only (licence: NONE) · get_code("d5d54c2f4ad20f9e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, amith-ananthram/see-it-from-my-perspective 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

Vision-language models (VLMs) can respond to queries about images in many languages. However, beyond language, culture affects how we see things. For example, individuals from Western cultures focus more on the central figure in an image while individuals from East Asian cultures attend more to scene context (Nisbett et al., 2001). In this work, we characterize the Western bias of VLMs in image understanding and investigate the role that language plays in this disparity. We evaluate VLMs across subjective and objective visual tasks with culturally diverse images and annotations. We find that VLMs perform better on the Western split than on the East Asian split of each task. Through controlled experimentation, we trace one source of this bias in image understanding to the lack of diversity in language model construction. While inference in a language nearer to a culture can lead to reductions in bias, we show it is much more effective when that language was well-represented during text-only pre-training. Interestingly, this yields bias reductions even when prompting in English. Our work highlights the importance of richer representation of all languages in building equitable VLMs. We make both our code and our models available at https://github.com/ amith-ananthram/see-it-from-my-perspective.

For agents

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

get_harvested_code_for_paper("2406.11665")
get_code_for_paper("2406.11665")
have("2406.11665")

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

curl https://syntology.ai/api/ran/2406.11665.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.11665.svg)](https://syntology.ai/paper/2406.11665)

Connect an agent — have() is free.