用知识图谱增强小模型，让手机助手更准更快理解用户指令。
NOEM$^{3}$A: a Neuro-symbolic Ontology-Enhanced Method for Multi-intent understanding in Mobile Agents
- 引入轻量级符号层，将意图本体注入小模型输入输出
- 在多轮对话数据集上提升准确率与槽位识别效果
- 适合对隐私和响应速度要求高的本地化智能设备
移动代理需在严苛延迟与隐私限制下，将自然语言请求映射为可执行意图。单纯扩大语言模型规模效率低下。我们提出NOEM³A，一种轻量级神经符号层，为紧凑型语言模型注入意图本体。针对每个查询，该方法检索小范围本体邻域，将候选动作标签注入提示词，并采用分词级解码先验确保输出合法性。这在输入输出表征中融入了符号化意图结构，同时保持本地交互的推理效率。我们还引入层次感知的语义意图相似度（SIS），通过本体深度捕捉词汇不同但语义相近的意图。在MultiWOZ 2.3对话数据集上的实验表明，本体增强显著提升了TinyLlama和Llama-3.2-3B在精确匹配与槽位F1上的表现。结果表明，符号对齐是实现精准、快速且隐私安全的本地化自然语言理解的有效策略。
原文摘要 · Abstract (English)
Mobile agents must map natural-language requests to executable intents under tight latency and privacy constraints. Scaling the language model is often an inefficient way to improve this component. We present NOEM$^{3}$A, a lightweight neuro-symbolic layer that augments compact language models with an intent ontology. For each query, NOEM$^{3}$A retrieves a small ontology neighborhood, injects candidate action labels into the prompt and applies a token-level decoding prior toward valid labels. This injects symbolic intent structure into both input and output representations while keeping inference suitable for local interaction. We also use Semantic Intent Similarity (SIS), a hierarchy-aware diagnostic based on ontology depth, to capture semantic proximity when predicted intents differ lexically. Experiments on MultiWOZ 2.3 dialogues show that ontology augmentation consistently improves TinyLlama and Llama-3.2-3B on exact match and Slot-F1. Our results suggest that symbolic alignment is an effective strategy for accurate, responsive and privacy-preserving on-device NLU.
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。