BiNSGPS: Geometry Problem Solving via Bidirectional Neuro-Symbolic Interaction
For AI researchers tackling geometry problem solving, this work addresses the brittleness of unidirectional neuro-symbolic pipelines by enabling dynamic error correction.
BiNSGPS introduces bidirectional interaction between a multimodal LLM and a symbolic solver for geometry problem solving, achieving 89.7% accuracy on Geometry3K and 78.1% on PGPS9K, outperforming prior unidirectional methods by over 10%.
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.