Saved in:
Bibliographic Details
Main Authors: Shim, Jungwoo, Kim, Dae Won, Kim, Sun Wook, Kim, Soo Young, Lee, Myungcheol, Cha, Jae-geun, Choi, Hyunhwa
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.16045
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915868377612288
author Shim, Jungwoo
Kim, Dae Won
Kim, Sun Wook
Kim, Soo Young
Lee, Myungcheol
Cha, Jae-geun
Choi, Hyunhwa
author_facet Shim, Jungwoo
Kim, Dae Won
Kim, Sun Wook
Kim, Soo Young
Lee, Myungcheol
Cha, Jae-geun
Choi, Hyunhwa
contents Small language models (sLLMs) are increasingly deployed on-device, where imperfect user prompts--typos, unclear intent, or missing context--can trigger factual errors and hallucinations. Existing automatic prompt optimization (APO) methods were designed for large cloud LLMs and rely on search that often produces long, structured instructions; when executed under an on-device constraint where the same small model must act as optimizer and solver, these pipelines can waste context and even hurt accuracy. We propose POaaS, a minimal-edit prompt optimization layer that routes each query to lightweight specialists (Cleaner, Paraphraser, Fact-Adder) and merges their outputs under strict drift and length constraints, with a conservative skip policy for well-formed prompts. Under a strict fixed-model setting with Llama-3.2-3B-Instruct and Llama-3.1-8B-Instruct, POaaS improves both task accuracy and factuality while representative APO baselines degrade them, and POaaS recovers up to +7.4% under token deletion and mixup. Overall, per-query conservative optimization is a practical alternative to search-heavy APO for on-device sLLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2603_16045
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle POaaS: Minimal-Edit Prompt Optimization as a Service to Lift Accuracy and Cut Hallucinations on On-Device sLLMs
Shim, Jungwoo
Kim, Dae Won
Kim, Sun Wook
Kim, Soo Young
Lee, Myungcheol
Cha, Jae-geun
Choi, Hyunhwa
Artificial Intelligence
Small language models (sLLMs) are increasingly deployed on-device, where imperfect user prompts--typos, unclear intent, or missing context--can trigger factual errors and hallucinations. Existing automatic prompt optimization (APO) methods were designed for large cloud LLMs and rely on search that often produces long, structured instructions; when executed under an on-device constraint where the same small model must act as optimizer and solver, these pipelines can waste context and even hurt accuracy. We propose POaaS, a minimal-edit prompt optimization layer that routes each query to lightweight specialists (Cleaner, Paraphraser, Fact-Adder) and merges their outputs under strict drift and length constraints, with a conservative skip policy for well-formed prompts. Under a strict fixed-model setting with Llama-3.2-3B-Instruct and Llama-3.1-8B-Instruct, POaaS improves both task accuracy and factuality while representative APO baselines degrade them, and POaaS recovers up to +7.4% under token deletion and mixup. Overall, per-query conservative optimization is a practical alternative to search-heavy APO for on-device sLLMs.
title POaaS: Minimal-Edit Prompt Optimization as a Service to Lift Accuracy and Cut Hallucinations on On-Device sLLMs
topic Artificial Intelligence
url https://arxiv.org/abs/2603.16045