SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.01960 · 2023

Language Models as Knowledge Bases for Visual Word Sense Disambiguation

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 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; 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/2310.01960.json · badge: /api/ran/2310.01960.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
anastasiakrith/llm-for-vwsd canonical (classifier label)
classifier basis: census
4 ran · 1 no recorded run
FunctionStatusWhere it lives
CoT_prompt Ran
ran; our contract draft was wrong, not the code
anastasiakrith/llm-for-vwsd/modules/prompts.py
pointer only (licence: NONE) · get_code("e4a5fab751465606")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, anastasiakrith/llm-for-vwsd 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_k_default_value Ran
ran, honoured the contract we drafted
anastasiakrith/llm-for-vwsd/qa_retrieval_eval.py
pointer only (licence: NONE); the stored copy get_code serves, from anastasiakrith/multimodal-retrieval-for-vwsd, is pointer only (licence: NONE) · get_code("f3ce5fa0f9d664c2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, anastasiakrith/llm-for-vwsd 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.

no_CoT_prompt Ran
ran; our contract draft was wrong, not the code
anastasiakrith/llm-for-vwsd/modules/prompts.py
pointer only (licence: NONE) · get_code("5ee88d1ab88ef45c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, anastasiakrith/llm-for-vwsd 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.

think_prompt Ran
ran; our contract draft was wrong, not the code
anastasiakrith/llm-for-vwsd/modules/prompts.py
pointer only (licence: NONE) · get_code("d8e8c3be701c6eb7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, anastasiakrith/llm-for-vwsd 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.

clean_captions Not yet run
unverified (harvested, no recorded run)
anastasiakrith/llm-for-vwsd/modules/captioners.py
pointer only (licence: NONE) · get_code("a2fb77ded7a905fa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, anastasiakrith/llm-for-vwsd 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 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 1 the same month, 0 later) and 4 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
get_k_default_value 1 other paper
1 the same month
2310.14025 (2023-10)
Large Language Models and Multimodal Retrieval for Visual Word Sense Disambiguation

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

Visual Word Sense Disambiguation (VWSD) is a novel challenging task that lies between linguistic sense disambiguation and fine-grained multimodal retrieval. The recent advancements in the development of visiolinguistic (VL) transformers suggest some off-the-self implementations with encouraging results, which however we argue that can be further improved. To this end, we propose some knowledge-enhancement techniques towards improving the retrieval performance of VL transformers via the usage of Large Language Models (LLMs) as Knowledge Bases. More specifically, knowledge stored in LLMs is retrieved with the help of appropriate prompts in a zero-shot manner, achieving performance advancements. Moreover, we convert VWSD to a purely textual question-answering (QA) problem by considering generated image captions as multiple-choice candidate answers. Zero-shot and few-shot prompting strategies are leveraged to explore the potential of such a transformation, while Chain-of-Thought (CoT) prompting in the zero-shot setting is able to reveal the internal reasoning steps an LLM follows to select the appropriate candidate. In total, our presented approach is the first one to analyze the merits of exploiting knowledge stored in LLMs in different ways to solve WVSD.

For agents

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

get_harvested_code_for_paper("2310.01960")
get_code_for_paper("2310.01960")
have("2310.01960")

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

curl https://syntology.ai/api/ran/2310.01960.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.01960.svg)](https://syntology.ai/paper/2310.01960)

Connect an agent — have() is free.