DANA用符号知识提升大模型可靠性，金融任务准确率超90%
DANA: Domain-Aware Neurosymbolic Agents for Consistency and Accuracy
- 融合领域知识的神经符号架构，双通道处理自然语言与逻辑符号
- 在FinanceBench上实现90%以上准确率，显著优于现有大模型系统
- 适合需要高可靠性的工业场景，如半导体制造中的复杂决策
大语言模型虽能力突出，但其固有的概率特性常导致复杂任务中结果不一致、不准确。本文提出DANA（领域感知神经符号智能体），通过整合领域知识与神经符号方法解决该问题。我们从神经符号视角分析AutoGPT、LangChain ReAct及OpenAI ChatGPT等当前架构，指出其依赖概率推理导致输出不稳定。DANA以自然语言和符号形式同时捕获并应用领域专长，实现更确定、可靠的推理行为。我们在开源OpenSSA框架中实现基于层级任务计划（HTPs）的DANA变体，在FinanceBench金融分析基准上取得超过90%的准确率，显著优于现有基于LLM的系统。在半导体等物理产业的应用表明，DANA灵活的知识融合架构能有效缓解大模型的概率性局限，具备解决需高精度与可靠性的真实世界复杂问题的潜力。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have shown remarkable capabilities, but their inherent probabilistic nature often leads to inconsistency and inaccuracy in complex problem-solving tasks. This paper introduces DANA (Domain-Aware Neurosymbolic Agent), an architecture that addresses these issues by integrating domain-specific knowledge with neurosymbolic approaches. We begin by analyzing current AI architectures, including AutoGPT, LangChain ReAct and OpenAI's ChatGPT, through a neurosymbolic lens, highlighting how their reliance on probabilistic inference contributes to inconsistent outputs. In response, DANA captures and applies domain expertise in both natural-language and symbolic forms, enabling more deterministic and reliable problem-solving behaviors. We implement a variant of DANA using Hierarchical Task Plans (HTPs) in the open-source OpenSSA framework. This implementation achieves over 90\% accuracy on the FinanceBench financial-analysis benchmark, significantly outperforming current LLM-based systems in both consistency and accuracy. Application of DANA in physical industries such as semiconductor shows that its flexible architecture for incorporating knowledge is effective in mitigating the probabilistic limitations of LLMs and has potential in tackling complex, real-world problems that require reliability and precision.
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。