SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.10404 · 2023

LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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; 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/2310.10404.json · badge: /api/ran/2310.10404.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
rlqja1107/torch-LLM4SGG canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
add_conv Ran
ran; our contract draft was wrong, not the code
rlqja1107/torch-LLM4SGG/maskrcnn_benchmark/layers/deform_pool.py
pointer only (licence: NONE) · get_code("3857170c2d5eb61d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rlqja1107/torch-LLM4SGG 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.

add_sepconv Ran
ran; our contract draft was wrong, not the code
rlqja1107/torch-LLM4SGG/maskrcnn_benchmark/layers/deform_pool.py
pointer only (licence: NONE) · get_code("33363ef0803b607a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rlqja1107/torch-LLM4SGG 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.

interpolate Ran
ran; our contract draft was wrong, not the code
rlqja1107/torch-LLM4SGG/maskrcnn_benchmark/layers/misc.py
pointer only (licence: NONE); the stored copy get_code serves, from KanghoonYoon/torch-rasgg, is pointer only (licence: NONE) · get_code("2902bf4410253ff7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rlqja1107/torch-LLM4SGG 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_divisible Ran
ran, honoured the contract we drafted
rlqja1107/torch-LLM4SGG/maskrcnn_benchmark/layers/deform_pool.py
pointer only (licence: NONE) · get_code("3592f11df8bd6c1d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rlqja1107/torch-LLM4SGG 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.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 4 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
interpolate 38 other papers
30 dated earlier, 7 later, 1 same year, order not determinable
1703.06870 (2017-03)
Mask R-CNN
1803.03243 (2018-03)
Domain Adaptive Faster R-CNN for Object Detection in the Wild
1807.08865 (2018-07)
StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction
and 35 more not named here
make_divisible 8 other papers
5 dated earlier, 3 later · 1 only as an assembly brick
1801.04381 (2018-01)
MobileNetV2: Inverted Residuals and Linear Bottlenecks
1811.12596 (2018-11)
Parsing R-CNN for Instance-Level Human Analysis
2209.12213 (2022-09)
ECO-TR: Efficient Correspondences Finding Via Coarse-to-Fine Refinement
and 5 more not named here
add_conv 4 other papers
2 dated earlier, 2 later
2305.18980 (2023-05)
Multi-modal Queried Object Detection in the Wild
2306.14060 (2023-06)
DesCo: Learning Object Recognition with Rich Language Descriptions
Chen_DViN_Dynamic_Visual_Routing_Network_for_Weakly_Supervised_Referring_Expression_CVPR_2025_paper (2025 (year only))
DViN: Dynamic Visual Routing Network for Weakly Supervised Referring Expression Comprehension
and 1 more not named here
add_sepconv 3 other papers
2 dated earlier, 1 later
2305.18980 (2023-05)
Multi-modal Queried Object Detection in the Wild
2306.14060 (2023-06)
DesCo: Learning Object Recognition with Rich Language Descriptions
Min_Vision-Language_Interactive_Relation_Mining_for_Open-Vocabulary_Scene_Graph_Generation_ICCV_2025_paper (2025 (year only))
Vision-Language Interactive Relation Mining for Open-Vocabulary Scene Graph Generation

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

Weakly-Supervised Scene Graph Generation (WSSGG) research has recently emerged as an alternative to the fully-supervised approach that heavily relies on costly annotations. In this regard, studies on WSSGG have utilized image captions to obtain unlocalized triplets while primarily focusing on grounding the unlocalized triplets over image regions. However, they have overlooked the two issues involved in the triplet formation process from the captions: 1) Semantic over-simplification issue arises when extracting triplets from captions, where fine-grained predicates in captions are undesirably converted into coarse-grained predicates, resulting in a long-tailed predicate distribution, and 2) Low-density scene graph issue arises when aligning the triplets in the caption with entity/predicate classes of interest, where many triplets are discarded and not used in training, leading to insufficient supervision. To tackle the two issues, we propose a new approach, i.e., Large Language Model for weakly-supervised SGG (LLM4SGG), where we mitigate the two issues by leveraging the LLM's in-depth understanding of language and reasoning ability during the extraction of triplets from captions and alignment of entity/predicate classes with target data. To further engage the LLM in these processes, we adopt the idea of Chain-of-Thought and the in-context few-shot learning strategy. To validate the effectiveness of LLM4SGG, we conduct extensive experiments on Visual Genome and GQA datasets, showing significant improvements in both Recall@K and mean Recall@K compared to the state-of-the-art WSSGG methods. A further appeal is that LLM4SGG is data-efficient, enabling effective model training with a small amount of training images.

For agents

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

get_harvested_code_for_paper("2310.10404")
get_code_for_paper("2310.10404")
have("2310.10404")

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

curl https://syntology.ai/api/ran/2310.10404.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.10404.svg)](https://syntology.ai/paper/2310.10404)

Connect an agent — have() is free.