用开源模型自动生成更匹配用户需求的系统提示。
System Message Generation for User Preferences using Open-Source Models
- 基于已有标注数据构建生成管道，自动补全系统消息。
- 在单轮和多轮对话测试中表现显著提升，尤其擅长快速建立有效交互。
- 适合需要高效定制对话角色与风格的开发者或应用团队。
系统消息在大语言模型交互中至关重要，常用于引导对话，赋予角色、任务背景、输出格式与沟通风格。然而公开数据集普遍缺少系统消息，且工业应用受版权限制；手动标注成本高。为此，我们提出SysGen，一种利用现有监督微调数据集生成与用户指令高度对齐的系统消息的流程。将开源模型在SysGen数据上训练后，在单轮（Multifacet）和多轮（SysBench）对话基准上均取得显著提升。尤其在短对话中优势明显，表明该方法能增强早期交互效率。定性分析进一步显示，多样且结构化的系统消息可显著提升LLM在不同场景下的适应能力。
原文摘要 · Abstract (English)
System messages play a crucial role in interactions with large language models (LLMs), often serving as prompts to initiate conversations. Through system messages, users can assign specific roles, perform intended tasks, incorporate background information, and specify various output formats and communication styles. Despite such versatility, publicly available datasets often lack system messages and are subject to strict license constraints in industrial applications. Moreover, manually annotating system messages that align with user instructions is resource-intensive. In light of these challenges, we introduce SysGen, a pipeline for generating system messages that better align assistant responses with user instructions using existing supervised fine-tuning datasets that lack system messages. Training open-source models on SysGen data yields substantial improvements in both single-turn (Multifacet) and multi-turn (SysBench) conversation benchmarks. Notably, our method shows strong gains in shorter conversations, suggesting that it enhances early-stage interaction effectiveness. Our qualitative analysis further emphasizes the value of diverse and structured system messages in improving LLM adaptability across varied user scenarios.
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。