@inproceedings{kim-etal-2026-dont,
title = "Don{'}t Generate, Classify! Low-Latency Prompt Optimization with Structured Complementary Prompt",
author = "Kim, Hee-Soo and
Kim, Jun-Young and
Lee, Jeong-Hwan and
Park, Seong-Jin and
Kim, Kang-Min",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-long.204/",
pages = "4364--4383",
ISBN = "979-8-89176-380-7",
abstract = "Large language models (LLMs) have demonstrated strong performance across diverse natural language processing tasks. However, their performance varies significantly across different prompts, requiring careful engineering for consistent results. Manual prompt engineering requires substantial human effort and suffers from limited reproducibility. In contrast, automatic prompt optimization methods reduce manual effort but often depend on costly autoregressive generation, resulting in substantial latency overheads. To address these limitations, we present low-latency prompt optimization (LLPO), a novel framework that reframes prompt engineering as a classification problem. LLPO classifies structured prompt fields from user input through multi-task classification and populates a predefined template to generate an optimized system prompt with minimal latency. In LLM-based automatic evaluations across four question-answering benchmarks, LLPO improves answer quality by up to 26.5{\%} in {\ensuremath{\Delta}}win rate compared to prior automatic prompt optimization methods, while reducing latency by up to 1,956 times. Human evaluation shows that LLPO receives the highest proportion of top-ranked responses. Furthermore, we analyze the contribution of each structured prompt field to performance, highlighting the robustness of our framework."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2026-dont">
<titleInfo>
<title>Don’t Generate, Classify! Low-Latency Prompt Optimization with Structured Complementary Prompt</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hee-Soo</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun-Young</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeong-Hwan</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seong-Jin</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kang-Min</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-380-7</identifier>
</relatedItem>
<abstract>Large language models (LLMs) have demonstrated strong performance across diverse natural language processing tasks. However, their performance varies significantly across different prompts, requiring careful engineering for consistent results. Manual prompt engineering requires substantial human effort and suffers from limited reproducibility. In contrast, automatic prompt optimization methods reduce manual effort but often depend on costly autoregressive generation, resulting in substantial latency overheads. To address these limitations, we present low-latency prompt optimization (LLPO), a novel framework that reframes prompt engineering as a classification problem. LLPO classifies structured prompt fields from user input through multi-task classification and populates a predefined template to generate an optimized system prompt with minimal latency. In LLM-based automatic evaluations across four question-answering benchmarks, LLPO improves answer quality by up to 26.5% in \ensuremathΔwin rate compared to prior automatic prompt optimization methods, while reducing latency by up to 1,956 times. Human evaluation shows that LLPO receives the highest proportion of top-ranked responses. Furthermore, we analyze the contribution of each structured prompt field to performance, highlighting the robustness of our framework.</abstract>
<identifier type="citekey">kim-etal-2026-dont</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-long.204/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>4364</start>
<end>4383</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Don’t Generate, Classify! Low-Latency Prompt Optimization with Structured Complementary Prompt
%A Kim, Hee-Soo
%A Kim, Jun-Young
%A Lee, Jeong-Hwan
%A Park, Seong-Jin
%A Kim, Kang-Min
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-380-7
%F kim-etal-2026-dont
%X Large language models (LLMs) have demonstrated strong performance across diverse natural language processing tasks. However, their performance varies significantly across different prompts, requiring careful engineering for consistent results. Manual prompt engineering requires substantial human effort and suffers from limited reproducibility. In contrast, automatic prompt optimization methods reduce manual effort but often depend on costly autoregressive generation, resulting in substantial latency overheads. To address these limitations, we present low-latency prompt optimization (LLPO), a novel framework that reframes prompt engineering as a classification problem. LLPO classifies structured prompt fields from user input through multi-task classification and populates a predefined template to generate an optimized system prompt with minimal latency. In LLM-based automatic evaluations across four question-answering benchmarks, LLPO improves answer quality by up to 26.5% in \ensuremathΔwin rate compared to prior automatic prompt optimization methods, while reducing latency by up to 1,956 times. Human evaluation shows that LLPO receives the highest proportion of top-ranked responses. Furthermore, we analyze the contribution of each structured prompt field to performance, highlighting the robustness of our framework.
%U https://aclanthology.org/2026.eacl-long.204/
%P 4364-4383
Markdown (Informal)
[Don’t Generate, Classify! Low-Latency Prompt Optimization with Structured Complementary Prompt](https://aclanthology.org/2026.eacl-long.204/) (Kim et al., EACL 2026)
ACL