SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.11713 · EMNLP · 2023

Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?

Haitian Sun, Ming-Wei Chang, Hexiang Hu, Soravit Changpinyo, Yang Chen, Yi Luan, Alan Ritter

arXiv · PDF · Open in the Atlas

Code that ran

3 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, 1 violated it and 0 have no contract verdict; 1 failure of our instrument; 3 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/2302.11713.json · badge: /api/ran/2302.11713.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
edchengg/infoseek_eval canonical (classifier label)
classifier basis not recorded on the link
3 ran · 3 no recorded run
FunctionStatusWhere it lives
exact_match_score Ran
ran, violated the contract we drafted
edchengg/infoseek_eval/infoseek_eval.py
code served (permissive licence) · get_code("7055aa97f2bde50e")
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 bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 re
import string

def normalize_answer(text: str) -> str:
    """Normalize a given text by removing articles, punctuation, and white spaces, and converting to lowercase."""

    def remove_articles(text: str) -> str:
        return re.sub('\\b(a|an|the)\\b', ' ', text)

    def white_space_fix(text: str) -> str:
        return ' '.join(text.split())

    def remove_punctuation(text: str) -> str:
        return ''.join((ch for ch in text if ch not in set(string.punctuation)))

    def lowercase(text: str) -> str:
        return text.lower()
    return white_space_fix(remove_articles(remove_punctuation(lowercase(text))))

def exact_match_score(prediction: str, ground_truth: str) -> bool:
    """Check if the normalized prediction exactly matches the normalized ground truth."""
    return normalize_answer(prediction) == normalize_answer(ground_truth)


ARGS = {
    "prediction": "The quick brown fox jumps over the lazy dog.",
    "ground_truth": "the quick brown fox jumps over the lazy dog"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
metric_max_over_ground_truths Ran
ran, honoured the contract we drafted
edchengg/infoseek_eval/infoseek_eval.py
code served (permissive licence) · get_code("921382b550348607")
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 int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

def simple_metric_fn(prediction: str, ground_truth: str) -> int:
    """Simple metric that counts matching characters."""
    return sum(1 for p, g in zip(prediction, ground_truth) if p == g)

metric_fn = simple_metric_fn
prediction = "hello"
ground_truths = ["hello", "hallo", "jello"]

ARGS = {
    "metric_fn": metric_fn,
    "prediction": prediction,
    "ground_truths": ground_truths,
}
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 int, ndim 0, dtype family int, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
normalize_answer Ran
ran; our contract draft was wrong, not the code
edchengg/infoseek_eval/infoseek_eval.py
code served (permissive licence) · get_code("4925192ddc8dfa9a")
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 re
import string

# The function normalize_answer takes a single parameter: text (a string)
# It removes articles, punctuation, converts to lowercase, and fixes whitespace

ARGS = {
    "text": "The quick brown fox jumps over the lazy dog! Is this a test?"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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
create_eval_data Not yet run
unverified (harvested, no recorded run)
edchengg/infoseek_eval/run_training_lavis.py
code served (permissive licence) · get_code("b1220700b1491fae")
How it ran

no invocation recorded.

load_and_process_image Not yet run
unverified (harvested, no recorded run)
edchengg/infoseek_eval/run_blip2_infoseek.py
code served (permissive licence) · get_code("07a7b4b4ff7827a6")
How it ran

no invocation recorded.

process_images_in_batches Not yet run
unverified (harvested, no recorded run)
edchengg/infoseek_eval/run_blip2_infoseek.py
code served (permissive licence) · get_code("c21c5f2835c4a0d0")
How it ran

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, 5 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 2 the same month, 3 later) and 1 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
normalize_answer 2 other papers
2 later
2410.13360 (2024-10)
RAP: Retrieval-Augmented Personalization for Multimodal Large Language Models
2604.05818 (2026-04)
WikiSeeker: Rethinking the Role of Vision-Language Models in Knowledge-Based Visual Question Answering
exact_match_score 1 other paper
1 later
2604.05818 (2026-04)
WikiSeeker: Rethinking the Role of Vision-Language Models in Knowledge-Based Visual Question Answering
load_and_process_image 1 other paper
1 the same month
2302.11154 (2023-02)
Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities
metric_max_over_ground_truths 1 other paper
1 later
2604.05818 (2026-04)
WikiSeeker: Rethinking the Role of Vision-Language Models in Knowledge-Based Visual Question Answering
process_images_in_batches 1 other paper
1 the same month
2302.11154 (2023-02)
Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities

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

Pre-trained vision and language models (Chen et al., 2023b,a;Dai et al., 2023; Li et al., 2023b) have demonstrated state-of-the-art capabilities over existing tasks involving images and texts, including visual question answering. However, it remains unclear whether these models possess the capability to answer questions that are not only querying visual content but knowledge-intensive and informationseeking. In this study, we introduce INFOS-EEK 1 , a visual question answering dataset tailored for information-seeking questions that cannot be answered with only common sense knowledge. Using INFOSEEK, we analyze various pre-trained visual question answering models and gain insights into their characteristics. Our findings reveal that state-of-the-art pre-trained multi-modal models (e.g., PaLI-X, BLIP2, etc.) face challenges in answering visual information-seeking questions, but finetuning on the INFOSEEK dataset elicits models to use fine-grained knowledge that was learned during their pre-training. Furthermore, we show that accurate visual entity recognition can be used to improve performance on INFOSEEK by retrieving relevant documents, showing a significant space for improvement. * Work done when interned at Google 1 Our dataset is available at https:// open-vision-language.github.io/infoseek/.

For agents

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

get_harvested_code_for_paper("2302.11713")
get_code_for_paper("2302.11713")
have("2302.11713")

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

curl https://syntology.ai/api/ran/2302.11713.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.11713.svg)](https://syntology.ai/paper/2302.11713)

Connect an agent — have() is free.