SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.15397 · NeurIPS · 2024

IPO: Interpretable Prompt Optimization for Vision-Language Models

Yingjun Du, G Cees, Snoek, Wenfang Sun

arXiv · PDF · Open in the Atlas

Code that ran

9 of 11 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; 8 failures of our instrument; 2 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, measured 2026-11-22; 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/2410.15397.json · badge: /api/ran/2410.15397.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
lmsdss/IPO canonical (classifier label)
classifier basis: census
6 ran · 2 no recorded run
lmsdss/ipo canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
read_jsonl Ran
ran; our contract draft was wrong, not the code
lmsdss/ipo/optimization/eval_utils.py
pointer only (licence: NONE) · get_code("a4cf9d0d1ece601e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lmsdss/ipo 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.

basic_clean Ran
ran; our contract draft was wrong, not the code
lmsdss/IPO/clip/simple_tokenizer.py
pointer only (licence: NONE); the stored copy get_code serves, from ltpwy/MSCI, is pointer only (licence: NONE) · get_code("98f385d847636a3e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lmsdss/IPO 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.

call_openai_server_func Ran
ran; our contract draft was wrong, not the code
lmsdss/IPO/prompt_utils.py
pointer only (licence: NONE) · get_code("310edb478a4009a1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lmsdss/IPO 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.

call_openai_server_single_prompt Ran
ran; our contract draft was wrong, not the code
lmsdss/IPO/prompt_utils.py
pointer only (licence: NONE) · get_code("daa969a73f4f1e26")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lmsdss/IPO 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.

compute_ci95 Ran
ran, honoured the contract we drafted
lmsdss/IPO/parse_test_res.py
pointer only (licence: NONE) · get_code("ba26afd892405335")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lmsdss/IPO 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_pairs Ran
ran; our contract draft was wrong, not the code
lmsdss/IPO/clip/simple_tokenizer.py
pointer only (licence: NONE) · get_code("d919ae32e5e4e616")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lmsdss/IPO 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.

instruction_to_filename Ran
ran; our contract draft was wrong, not the code
lmsdss/ipo/optimization/eval_utils.py
pointer only (licence: NONE) · get_code("b1e17b573bb75a26")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lmsdss/ipo 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.

remove_punctuation_from_string Ran
ran; our contract draft was wrong, not the code
lmsdss/ipo/optimization/eval_utils.py
pointer only (licence: NONE) · get_code("dc0fb1ce4824c2c3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lmsdss/ipo 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.

whitespace_clean Ran
ran; our contract draft was wrong, not the code
lmsdss/IPO/clip/simple_tokenizer.py
pointer only (licence: NONE); the stored copy get_code serves, from ltpwy/MSCI, is pointer only (licence: NONE) · get_code("9542161e9640b858")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lmsdss/IPO 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.

build_model Not yet run
unverified (harvested, no recorded run)
lmsdss/IPO/clip/model.py
pointer only (licence: NONE); the stored copy get_code serves, from Sheldon04/NeRP, is pointer only (licence: NONE) · get_code("c47aa9e5b049a11d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lmsdss/IPO 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.

load Not yet run
unverified (harvested, no recorded run)
lmsdss/IPO/clip/clip.py
pointer only (licence: NONE) · get_code("1b5c9c827d9060b5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lmsdss/IPO 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 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 9 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 5 the same month, 5 later) and 2 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_pairs 258 other papers
180 dated earlier, 10 the same month, 60 later, 7 same year, order not determinable, 1 undated · 4 only as an assembly brick
1802.06474 (2018-02)
A Closed-form Solution to Photorealistic Image Stylization
1803.01128 (2018-03)
Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples
1809.00125 (2018-09)
Simple Fusion: Return of the Language Model
and 255 more not named here
whitespace_clean 231 other papers
159 dated earlier, 9 the same month, 55 later, 7 same year, order not determinable, 1 undated · 4 only as an assembly brick
1901.07441 (2019-01)
PadChest: A large chest x-ray image dataset with multi-label annotated reports
2107.06383 (2021-07)
How Much Can CLIP Benefit Vision-and-Language Tasks?
2108.10904 (2021-08)
SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
and 228 more not named here
basic_clean 218 other papers
159 dated earlier, 9 the same month, 42 later, 7 same year, order not determinable, 1 undated · 4 only as an assembly brick
1901.07441 (2019-01)
PadChest: A large chest x-ray image dataset with multi-label annotated reports
2107.06383 (2021-07)
How Much Can CLIP Benefit Vision-and-Language Tasks?
2108.10904 (2021-08)
SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
and 215 more not named here
build_model 119 other papers
88 dated earlier, 1 the same month, 23 later, 5 same year, order not determinable, 2 undated
1809.11096 (2018-09)
Large Scale GAN Training for High Fidelity Natural Image Synthesis
1901.07441 (2019-01)
PadChest: A large chest x-ray image dataset with multi-label annotated reports
2104.14294 (2021-04)
Emerging Properties in Self-Supervised Vision Transformers
and 116 more not named here
compute_ci95 37 other papers
24 dated earlier, 3 the same month, 6 later, 3 same year, order not determinable, 1 undated
2106.00592 (2021-06)
Semi-Supervised Domain Generalization with Stochastic StyleMatch
2203.05557 (2022-03)
Conditional Prompt Learning for Vision-Language Models
2203.07740 (2022-03)
Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization
and 34 more not named here
call_openai_server_func 1 other paper
1 dated earlier
2309.03409 (2023-09)
Large Language Models as Optimizers
call_openai_server_single_prompt 1 other paper
1 dated earlier
2309.03409 (2023-09)
Large Language Models as Optimizers
read_jsonl 1 other paper
1 dated earlier
2309.03409 (2023-09)
Large Language Models as Optimizers
remove_punctuation_from_string 1 other paper
1 dated earlier
2309.03409 (2023-09)
Large Language Models as Optimizers

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-language models like CLIP have remarkably adapted to various downstream tasks. Nonetheless, their performance heavily depends on the specificity of the input text prompts, which requires skillful prompt template engineering. Instead, current approaches to prompt optimization learn the prompts through gradient descent, where the prompts are treated as adjustable parameters. However, these methods tend to lead to overfitting of the base classes seen during training and produce prompts that are no longer understandable by humans. This paper introduces a simple but interpretable prompt optimizer (IPO), that utilizes large language models (LLMs) to generate textual prompts dynamically. We introduce a Prompt Optimization Prompt that not only guides LLMs in creating effective prompts but also stores past prompts with their performance metrics, providing rich in-context information. Additionally, we incorporate a large multimodal model (LMM) to condition on visual content by generating image descriptions, which enhance the interaction between textual and visual modalities. This allows for the creation of dataset-specific prompts that improve generalization performance, while maintaining human comprehension. Extensive testing across 11 datasets reveals that IPO not only improves the accuracy of existing gradient-descent-based prompt learning methods but also considerably enhances the interpretability of the generated prompts. By leveraging the strengths of LLMs, our approach ensures that the prompts remain human-understandable, thereby facilitating better transparency and oversight for vision-language models.

For agents

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

get_harvested_code_for_paper("2410.15397")
get_code_for_paper("2410.15397")
have("2410.15397")

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

curl https://syntology.ai/api/ran/2410.15397.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.15397.svg)](https://syntology.ai/paper/2410.15397)

Connect an agent — have() is free.