# POaaS: Minimal-Edit Prompt Optimization as a Service to Lift Accuracy and Cut Hallucinations on On-Device sLLMs

Source: [POaaS: Minimal-Edit Prompt Optimization as a Service to Lift Accuracy and Cut Hallucinations on On-Device sLLMs](<https://www.sota2.com/research/paper/69ba31a80636e5bf4afc096d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-19T05:00:05.030Z

Authors: Jungwoo Shim, Dae Won Kim, Sun Wook Kim, Soo Young Kim, Myungcheol Lee, Jae-geun Cha, Hyunhwa Choi

Published: 2026-03-17T01:05:39.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Prompt Optimization Efficiency on BBH, GSM8K, and CSQA (test)](<https://www.sota2.com/research/sota/prompt-optimization-efficiency-on-bbh-gsm8k-and-csqa-test.md>): Prompt Optimization Efficiency; BBH, GSM8K, and CSQA averaged (test); Opt. Time (s): 0.95.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.16045>)

[PDF](<https://arxiv.org/pdf/2603.16045.pdf>)
