本地模型协作推理时保护数据隐私，准确率提升超40%
Collaborative LLM Numerical Reasoning with Local Data Protection
- 本地模型改写问题主题，保留推理逻辑以避免泄露
- 用远程生成的代码片段重构答案，提升准确性16.2%~43.6%
- 适合移动端或隐私敏感场景的智能问答系统
文档中的数值推理需要上下文理解与逻辑推断，对计算资源受限设备上的低容量本地模型而言极具挑战。尽管可将复杂查询路由至强大远程模型（如GPT-4），但会引发数据泄露风险。现有方法通过生成问题描述或示例来缓解，但数值推理的复杂性导致本地模型难以生成等效查询，也无法准确依赖远程指导推断答案。本文提出一种模型协作框架，包含两项关键创新：(1) 上下文感知的问题主题重写策略，保持推理模式不变；(2) 基于工具的答案重构方法，复用远程生成的即插即用代码片段。实验表明，该方法在保持比纯本地模型更高推理准确率的同时，显著优于完全依赖远程模型的数据保护方案。相比现有保护方法，准确率提升16.2%–43.6%，数据泄露降低2.3%–44.6%。
原文摘要 · Abstract (English)
Numerical reasoning over documents, which demands both contextual understanding and logical inference, is challenging for low-capacity local models deployed on computation-constrained devices. Although such complex reasoning queries could be routed to powerful remote models like GPT-4, exposing local data raises significant data leakage concerns. Existing mitigation methods generate problem descriptions or examples for remote assistance. However, the inherent complexity of numerical reasoning hinders the local model from generating logically equivalent queries and accurately inferring answers with remote guidance. In this paper, we present a model collaboration framework with two key innovations: (1) a context-aware synthesis strategy that shifts the query topics while preserving reasoning patterns; and (2) a tool-based answer reconstruction approach that reuses the remote-generated plug-and-play solution with code snippets. Experimental results demonstrate that our method achieves better reasoning accuracy than solely using local models while providing stronger data protection than fully relying on remote models. Furthermore, our method improves accuracy by 16.2% - 43.6% while reducing data leakage by 2.3% - 44.6% compared to existing data protection approaches.
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。