轻量提示优化服务提升设备端小模型准确率，减少幻觉。
POaaS: Minimal-Edit Prompt Optimization as a Service to Lift Accuracy and Cut Hallucinations on On-Device sLLMs
- 设计轻量级专家路由系统，仅做最小修改优化提示。
- 在固定模型下提升准确率与事实性，最高恢复7.4%性能。
- 适合资源受限的设备端小模型应用，避免搜索开销。
小语言模型（sLLMs）正越来越多地部署在设备端，但用户输入的不完整、拼写错误或语义模糊提示常引发事实错误和幻觉。现有自动提示优化（APO）方法专为云端大模型设计，依赖搜索生成长而结构化的指令，在设备端受限环境下，同一小模型需同时担任优化器与求解器时，易浪费上下文甚至降低准确率。本文提出POaaS：一种最小修改提示优化服务，通过轻量专家（清理器、改写器、事实补充器）路由并合并输出，在严格控制漂移与长度的前提下，对已良好提示采用保守跳过策略。在固定模型设置下使用Llama-3.2-3B-Instruct和Llama-3.1-8B-Instruct测试，POaaS在任务准确率与事实性上均优于主流APO基线，且在删除和混杂测试中最高恢复7.4%性能。结果表明，保守的逐查询优化是设备端sLLMs更实用的替代方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。