@inproceedings{zhang-etal-2026-prompting-prompt,
title = "Prompting to Prompt: Meta-Template Learning for Transferable Prompt Optimization",
author = "Zhang, Xinyu and
Li, Deyang and
Zhao, Minjun and
Han, Meng and
Shi, Ruifeng and
Dou, Zhicheng",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.58/",
pages = "1187--1208",
ISBN = "979-8-89176-462-0",
abstract = "Existing prompt optimization methods often improve prompts for a specific task or deployment setting, but their optimized prompts transfer poorly to new tasks and usually require re-optimization. We propose Prompting to Prompt (PTP), a framework that learns meta-templates as structured intermediate representations for reusable prompt construction. PTP decomposes prompts into transferable elements and optimizes them with LLM-generated textual gradients. Its inner loop refines task-specific prompts from natural-language feedback and an element list, while its outer loop abstracts structural changes across tasks to update the meta-template.The learned meta-template is then reused for task-level and query-level prompt generation, reducing the need to rerun full prompt optimization for each target setting. Experiments on six benchmarks show gains in both offline transfer and test-time deployment settings, with improvements up to 10.52 points on Arena-Hard."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-prompting-prompt">
<titleInfo>
<title>Prompting to Prompt: Meta-Template Learning for Transferable Prompt Optimization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deyang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minjun</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meng</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhicheng</namePart>
<namePart type="family">Dou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Existing prompt optimization methods often improve prompts for a specific task or deployment setting, but their optimized prompts transfer poorly to new tasks and usually require re-optimization. We propose Prompting to Prompt (PTP), a framework that learns meta-templates as structured intermediate representations for reusable prompt construction. PTP decomposes prompts into transferable elements and optimizes them with LLM-generated textual gradients. Its inner loop refines task-specific prompts from natural-language feedback and an element list, while its outer loop abstracts structural changes across tasks to update the meta-template.The learned meta-template is then reused for task-level and query-level prompt generation, reducing the need to rerun full prompt optimization for each target setting. Experiments on six benchmarks show gains in both offline transfer and test-time deployment settings, with improvements up to 10.52 points on Arena-Hard.</abstract>
<identifier type="citekey">zhang-etal-2026-prompting-prompt</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.58/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1187</start>
<end>1208</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Prompting to Prompt: Meta-Template Learning for Transferable Prompt Optimization
%A Zhang, Xinyu
%A Li, Deyang
%A Zhao, Minjun
%A Han, Meng
%A Shi, Ruifeng
%A Dou, Zhicheng
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F zhang-etal-2026-prompting-prompt
%X Existing prompt optimization methods often improve prompts for a specific task or deployment setting, but their optimized prompts transfer poorly to new tasks and usually require re-optimization. We propose Prompting to Prompt (PTP), a framework that learns meta-templates as structured intermediate representations for reusable prompt construction. PTP decomposes prompts into transferable elements and optimizes them with LLM-generated textual gradients. Its inner loop refines task-specific prompts from natural-language feedback and an element list, while its outer loop abstracts structural changes across tasks to update the meta-template.The learned meta-template is then reused for task-level and query-level prompt generation, reducing the need to rerun full prompt optimization for each target setting. Experiments on six benchmarks show gains in both offline transfer and test-time deployment settings, with improvements up to 10.52 points on Arena-Hard.
%U https://aclanthology.org/2026.findings-emnlp.58/
%P 1187-1208
Markdown (Informal)
[Prompting to Prompt: Meta-Template Learning for Transferable Prompt Optimization](https://aclanthology.org/2026.findings-emnlp.58/) (Zhang et al., Findings 2026)
ACL