@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://preview.aclanthology.org/ingest-eacl/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."
}