推进大语言模型中的符号积分：超越传统神经符号人工智能
Advancing Symbolic Integration in Large Language Models: Beyond Conventional Neurosymbolic AI
AI总结：
本文提出一种新的LLMs符号集成分类法及四维路线图，以解决LLMs透明度不足的问题，并推动符号技术与LLMs的有效融合。
摘要：
大语言模型（LLMs）在高风险领域已展现出高效学习、类人响应生成和决策能力。然而，这些模型仍然是黑盒，因为它们难以确保响应的透明度。文献中已探索了多种方法来解决LLMs中的透明度挑战，包括神经符号人工智能（NeSy AI）。NeSy AI方法主要针对传统神经网络开发，并不完全适用于LLMs的独特特征。因此，对于如何将符号人工智能有效集成到LLMs中，目前缺乏系统的理解。本文旨在通过首先回顾已建立的NeSy AI方法，然后提出一种新的LLMs中符号集成分类法，以及将符号技术与LLMs融合的路线图，来填补这一空白。该路线图引入了一个跨四个维度的新分类框架，通过在这些类别中组织现有文献。这些维度包括：LLM各个阶段的符号集成、耦合机制、架构范式，以及算法和应用层面的视角。本文全面识别了当前基准、前沿进展和领域内的关键空白，以提出未来研究的路线图。通过突出最新发展和文献中的显著空白，它为实施符号集成到LLMs中的框架提供了实用见解，以增强透明度。
英文摘要：
LLMs have demonstrated highly effective learning, human-like response generation,and decision-making capabilities in high-risk sectors. However, these models remain black boxes because they struggle to ensure transparency in responses. The literature has explored numerous approaches to address transparency challenges in LLMs, including Neurosymbolic AI (NeSy AI). NeSy AI approaches were primarily developed for conventional neural networks and are not well-suited to the unique features of LLMs. Consequently, there is a limited systematic understanding of how symbolic AI can be effectively integrated into LLMs. This paper aims to address this gap by first reviewing established NeSy AI methods and then proposing a novel taxonomy of symbolic integration in LLMs, along with a roadmap to merge symbolic techniques with LLMs. The roadmap introduces a new categorisation framework across four dimensions by organising existing literature within these categories. These include symbolic integration across various stages of LLM, coupling mechanisms, architectural paradigms, as well as algorithmic and application-level perspectives. The paper thoroughly identifies current benchmarks, cutting-edge advancements, and critical gaps within the field to propose a roadmap for future research. By highlighting the latest developments and notable gaps in the literature, it offers practical insights for implementing frameworks for symbolic integration into LLMs to enhance transparency.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
