@inproceedings{ding-etal-2026-automatic,
title = "Automatic Prompt Engineering for Scalable Prompt Inversion in Text-to-Image Ad Generation",
author = "Ding, Zixin and
Zeng, Qi and
Gong, Boying and
Deng, Wenlong and
Pan, Bo and
Chen, Yuxin",
editor = "Li, Yunyao and
Rehm, Georg and
Tu, Mei",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-industry.111/",
pages = "1605--1626",
ISBN = "979-8-89176-394-4",
abstract = "While prompt engineering offers effective control over Text-to-Image (T2I) generation, it remains labor-intensive for large-scale production. We present PRISM-DUEL, a black-box framework that formalizes prompt optimization as Automatic Prompt Engineering (APE), motivated by advertising workflows requiring low-latency, diverse variants faithful to a human-designed ads. Since zero-shot LLMs are unreliable judges of image quality, PRISM-DUEL obtains label-free pairwise preferences and rationales from an LLM judge over pairs of generated images, then uses a dueling-bandit optimizer to optimize a prompt for generating controlled variations while matching the reference ad{'}s visual content. By iteratively steering the prompt distribution towards higher-quality generations and improving posterior calibration, PRISM-DUEL preserves visual similarity and semantic faithfulness while increasing diversity. Experiments on PartiPrompts and DreamBooth across Gemini 2.5 Flash Image, FLUX.1, and Qwen-Image show consistent gains over strong baselines in visual faithfulness and prompt interpretability."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ding-etal-2026-automatic">
<titleInfo>
<title>Automatic Prompt Engineering for Scalable Prompt Inversion in Text-to-Image Ad Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zixin</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boying</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenlong</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxin</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mei</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-394-4</identifier>
</relatedItem>
<abstract>While prompt engineering offers effective control over Text-to-Image (T2I) generation, it remains labor-intensive for large-scale production. We present PRISM-DUEL, a black-box framework that formalizes prompt optimization as Automatic Prompt Engineering (APE), motivated by advertising workflows requiring low-latency, diverse variants faithful to a human-designed ads. Since zero-shot LLMs are unreliable judges of image quality, PRISM-DUEL obtains label-free pairwise preferences and rationales from an LLM judge over pairs of generated images, then uses a dueling-bandit optimizer to optimize a prompt for generating controlled variations while matching the reference ad’s visual content. By iteratively steering the prompt distribution towards higher-quality generations and improving posterior calibration, PRISM-DUEL preserves visual similarity and semantic faithfulness while increasing diversity. Experiments on PartiPrompts and DreamBooth across Gemini 2.5 Flash Image, FLUX.1, and Qwen-Image show consistent gains over strong baselines in visual faithfulness and prompt interpretability.</abstract>
<identifier type="citekey">ding-etal-2026-automatic</identifier>
<location>
<url>https://aclanthology.org/2026.acl-industry.111/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1605</start>
<end>1626</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Prompt Engineering for Scalable Prompt Inversion in Text-to-Image Ad Generation
%A Ding, Zixin
%A Zeng, Qi
%A Gong, Boying
%A Deng, Wenlong
%A Pan, Bo
%A Chen, Yuxin
%Y Li, Yunyao
%Y Rehm, Georg
%Y Tu, Mei
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-394-4
%F ding-etal-2026-automatic
%X While prompt engineering offers effective control over Text-to-Image (T2I) generation, it remains labor-intensive for large-scale production. We present PRISM-DUEL, a black-box framework that formalizes prompt optimization as Automatic Prompt Engineering (APE), motivated by advertising workflows requiring low-latency, diverse variants faithful to a human-designed ads. Since zero-shot LLMs are unreliable judges of image quality, PRISM-DUEL obtains label-free pairwise preferences and rationales from an LLM judge over pairs of generated images, then uses a dueling-bandit optimizer to optimize a prompt for generating controlled variations while matching the reference ad’s visual content. By iteratively steering the prompt distribution towards higher-quality generations and improving posterior calibration, PRISM-DUEL preserves visual similarity and semantic faithfulness while increasing diversity. Experiments on PartiPrompts and DreamBooth across Gemini 2.5 Flash Image, FLUX.1, and Qwen-Image show consistent gains over strong baselines in visual faithfulness and prompt interpretability.
%U https://aclanthology.org/2026.acl-industry.111/
%P 1605-1626
Markdown (Informal)
[Automatic Prompt Engineering for Scalable Prompt Inversion in Text-to-Image Ad Generation](https://aclanthology.org/2026.acl-industry.111/) (Ding et al., ACL 2026)
ACL