小模型通过分步解析，实现超越大模型的意图识别效果
Small Models, Big Results: Achieving Superior Intent Extraction through Decomposition
- 先结构化提炼每步操作关键信息，再用小模型处理汇总结果
- 在资源受限设备上实现意图识别性能超越基础大模型
- 适合注重隐私、低延迟的移动端智能助手场景
从用户界面交互轨迹中理解意图，仍是智能代理开发中的关键挑战。尽管大规模数据中心多模态大语言模型（MLLM）具备更强处理能力，但能在设备端运行的小模型因资源受限，难以准确推断意图。本文提出一种分解式新方法：首先对每一步用户操作进行结构化交互摘要，提取关键信息；其次使用微调后的模型基于聚合摘要完成意图提取。该方法显著提升小模型在资源受限环境下的意图理解能力，甚至优于基础大模型的表现。
原文摘要 · Abstract (English)
Understanding user intents from UI interaction trajectories remains a challenging, yet crucial, frontier in intelligent agent development. While massive, datacenter-based, multi-modal large language models (MLLMs) possess greater capacity to handle the complexities of such sequences, smaller models which can run on-device to provide a privacy-preserving, low-cost, and low-latency user experience, struggle with accurate intent inference. We address these limitations by introducing a novel decomposed approach: first, we perform structured interaction summarization, capturing key information from each user action. Second, we perform intent extraction using a fine-tuned model operating on the aggregated summaries. This method improves intent understanding in resource-constrained models, even surpassing the base performance of large MLLMs.
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。