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

TL;DR

SymbolicAI is a modular framework that integrates generative models with symbolic solvers, enabling complex, explainable workflows and benchmarking LLMs using a novel VERTEX score.

Contribution

It introduces a flexible, logic-based framework combining probabilistic programming, multi-modal data operations, and a new benchmarking score for LLMs in complex tasks.

Findings

Framework effectively bridges symbolic reasoning and generative AI.

Enables creation of explainable computational graphs.

Provides a new benchmark and VERTEX score for evaluating LLMs.

Abstract

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.