用符号推理增强大模型，让多语言长文本理解更准更可解释。
Enhancing Large Language Models with Neurosymbolic Reasoning for Multilingual Tasks
- 将文本提取为符号事实并生成可执行代码，实现分步推理
- 跨7种语言、多长度上下文下，准确率显著优于基线和提示策略
- 适合需要高可靠性和可解释性的多语言复杂任务场景
大语言模型在长文本中多目标推理时常因信息分散而表现不佳。为此，我们提出神经符号增强推理（NSAR），在推理阶段融合神经与符号推理优势。NSAR 显式从文本中提取符号事实，并生成可执行的 Python 代码以处理复杂推理步骤。在七种语言及多种上下文长度下的大量实验表明，NSAR 在准确识别与整合多条信息方面显著优于基础 RAG 基线和先进提示策略。结果表明，将显式符号操作与神经推理结合，能有效提升多语言场景下的鲁棒性、可解释性与可扩展性。
原文摘要 · Abstract (English)
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.
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。