Enhancing Large Language Models with Neurosymbolic Reasoning for Multilingual Tasks
This addresses the challenge of robust and interpretable reasoning in multilingual tasks for AI applications, representing a novel method rather than an incremental improvement.
The paper tackles the problem of large language models struggling with multi-target reasoning in long-context scenarios by introducing NeuroSymbolic Augmented Reasoning (NSAR), which combines neural and symbolic reasoning to extract facts and generate executable code, resulting in significant performance improvements over baselines across seven languages.
Large language models (LLMs) often struggle to perform multi-target reasoning in long-context scenarios where relevant information is scattered across extensive documents. To address this challenge, we introduce NeuroSymbolic Augmented Reasoning (NSAR), which combines the benefits of neural and symbolic reasoning during inference. NSAR explicitly extracts symbolic facts from text and generates executable Python code to handle complex reasoning steps. Through extensive experiments across seven languages and diverse context lengths, we demonstrate that NSAR significantly outperforms both a vanilla RAG baseline and advanced prompting strategies in accurately identifying and synthesizing multiple pieces of information. Our results highlight the effectiveness of combining explicit symbolic operations with neural inference for robust, interpretable, and scalable reasoning in multilingual settings.