arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.00854cs.LGcs.AIcs.SCcs.SE
收藏

SymbolicAI:一个结合生成模型与求解器的基于逻辑方法的框架

SymbolicAI: A framework for logic-based approaches combining generative models and solvers

ExtensityAI;Johannes Kepler University(约翰开普勒大学);RICAM;Amazon Devices(亚马逊设备)

Marius-Constantin Dinu, Claudiu Leoveanu-Condrei, Markus Holzleitner, Werner Zellinger, Sepp Hochreiter

AI总结:

本文提出SymbolicAI框架,将LLM作为语义解析器结合生成模型与求解器,利用概率与可微编程处理复杂任务,并引入VERTEX评分评估可解释计算图。

摘要:

我们介绍了SymbolicAI,这是一个多功能且模块化的框架,采用基于逻辑的方法来进行概念学习和生成过程中的流程管理。SymbolicAI通过将大型语言模型(LLMs)视为基于自然语言和形式语言指令执行任务的语义解析器,从而将生成模型与多种求解器无缝集成,弥合了符号推理与生成式AI之间的鸿沟。我们利用概率编程原则来处理复杂任务,并利用可微编程和经典编程范式及其各自的优势。该框架引入了一组用于多模态数据的多态、组合和自引用操作,这些操作连接了多步生成过程,并使其输出与复杂工作流中的用户目标对齐。因此,我们可以在具备上下文学习能力的各种基础模型的能力之间进行转换,也可以在擅长解决特定问题的专用、微调模型或求解器之间进行转换。通过这些基于上下文学习的操作,我们的框架能够创建和评估可解释的计算图。最后,我们引入了一种用于评估这些计算图的质量度量及其经验评分,并提出一个基准,用于比较各种最先进的LLMs在一系列复杂工作流中的表现。我们将该经验评分称为“通过交叉相似性进行关系轨迹评估的向量嵌入”,简称VERTEX评分。该框架的代码库和基准链接如下。

英文摘要:

We introduce SymbolicAI, a versatile and modular framework employing a logic-based approach to concept learning and flow management in generative processes. SymbolicAI enables the seamless integration of generative models with a diverse range of solvers by treating large language models (LLMs) as semantic parsers that execute tasks based on both natural and formal language instructions, thus bridging the gap between symbolic reasoning and generative AI. We leverage probabilistic programming principles to tackle complex tasks, and utilize differentiable and classical programming paradigms with their respective strengths. The framework introduces a set of polymorphic, compositional, and self-referential operations for multi-modal data that connects multi-step generative processes and aligns their outputs with user objectives in complex workflows. As a result, we can transition between the capabilities of various foundation models with in-context learning capabilities and specialized, fine-tuned models or solvers proficient in addressing specific problems. Through these operations based on in-context learning our framework enables the creation and evaluation of explainable computational graphs. Finally, we introduce a quality measure and its empirical score for evaluating these computational graphs, and propose a benchmark that compares various state-of-the-art LLMs across a set of complex workflows. We refer to the empirical score as the "Vector Embedding for Relational Trajectory Evaluation through Cross-similarity", or VERTEX score for short. The framework codebase and benchmark are linked below.

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。

↑