双向神经符号交互提升几何题求解准确率
BiNSGPS: Geometry Problem Solving via Bidirectional Neuro-Symbolic Interaction
- 构建双向反馈机制，让大模型与符号求解器动态协作
- 通过纠错和辅助假设生成，解决符号冲突问题
- 适合需要严谨推理的数学教育与AI竞赛场景
几何问题求解在人工智能中面临独特挑战。现有方法主要分为符号法和神经法：前者适应性差，后者易产生幻觉。当前的神经符号混合方法多采用单向流程，即神经模型输出直接输入求解器，缺乏反馈，对早期错误敏感。为突破这一瓶颈，本文提出BiNSGPS框架，建立大语言模型顾问（MLLM Adviser）与符号求解器之间的双向神经符号交互（BiNS）。MLLM顾问主动接收符号求解器的反馈，动态修正不一致的形式化表示或提出辅助假设，从而化解符号矛盾，支持复杂推理。
原文摘要 · Abstract (English)
Geometry problem solving poses distinct challenges in artificial intelligence. Existing approaches typically fall into two paradigms: symbolic methods, which exhibit limited adaptability, and neural methods, which are prone to hallucinations. Recent neuro-symbolic hybrids predominantly rely on a unidirectional pipeline where neural outputs are fed into solvers without feedback, making system brittle to early-stage errors. To break this unidirectional bottleneck, we propose BiNSGPS, a framework that establishes Bidirectional Neuro-Symbolic Interaction (BiNS) between a MLLM Adviser and a Symbolic Solver. MLLM Adviser actively incorporates feedback from the symbolic solver to dynamically rectify inconsistent formal representations or propose auxiliary hypotheses, resolving symbolic conflicts and facilitating complex deductions.
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。