Neuro-symbolic AI // structured and unstructured
Combination of neuro (data approximation) and symbolic (recursive logic) is still a promising field of research
Neuro-symbolic approach isn’t new, but now it can be enhanced/updated to get better results.
Corps aren’t sleeping..
LogiCity is a new simulator and benchmark for NeSy AI. It simulates dynamic urban environments with flexible abstractions. It features Inductive Abstract Reasoning, where the most recent LLM (GPT-4o) falls behind human.
Recent years have witnessed the rapid development of Neuro-Symbolic (NeSy) AI systems, which integrate symbolic reasoning into deep neural networks. However, most existing benchmarks for NeSy AI fail to provide long-horizon reasoning task with complex multi-agent interaction. Furthermore, they are usually constrained by fixed and simplistic logical rules over limited entities, making them inadequate for capturing real-world complexities.
To address these crucial gaps, we introduce LogiCity, the first simulator based on customizable first-order logic (FOL) for an urban-like environment with multiple dynamic agents. LogiCity models diverse urban elements using semantic and spatial concepts, such as IsAmbulance(X) and IsClose(X,Y). These concepts are used to define FOL rules governing the behavior of various agents. Since the concepts and rules are abstractions, they can be universally applied to cities with any agent compositions, facilitating the instantiation of diverse scenarios. Besides, a key benefit of our LogiCity is its support for user-configurable abstractions, enabling customizable simulation complexities for logical reasoning.
To explore various aspects of NeSy AI, we introduces two tasks, one features long-horizon sequential decision-making, and the other focuses on one-step visual reasoning, varying in difficulty and agent behaviors. Our extensive evaluation using LogiCity reveals the advantage of NeSy frameworks in abstract reasoning. Moreover, we highlight the significant challenges of handling more complex abstractions in long-horizon multi-agent reasoning scenarios or under high-dimensional, imbalanced data. With the flexible design, various features, and newly raised challenges, we believe LogiCity represents a pivotal step for advancing the next generation of NeSy AI.
Neurosymbolic Programming (NP) techniques have the potential to accelerate scientific discovery. These models combine neural and symbolic components to learn complex patterns and representations from data, using high-level concepts or known constraints. NP techniques can interface with symbolic domain knowledge from scientists, such as prior knowledge and experimental context, to produce interpretable outputs. We identify opportunities and challenges between current NP models and scientific workflows, with real-world examples from behavior analysis in science: to enable the use of NP broadly for workflows across the natural and social sciences.
Neurosymbolic programming offers the promise to accelerate scientific discovery and optimize scientific discovery end-to-end. The benefits are in its ability to incorporate prior knowledge and the symbolic nature of the solutions, essential scientific workflows. However, challenges still remain in scalability and optimization stability of these approaches, comprehensive evaluations, and deployment in the form of tools. In this paper, we have demonstrated the opportunities and challenges of neurosymbolic programming in a concrete scientific application, behavior analysis. A key promise of neurosymbolic programming is to provide a set of unifying principles in interpretable machine learning and prior scientific literature. We invite the science and computer science communities to adopt these methods in their scientific workflow and to contribute to the research to advance NP techniques for science due to the unique benefit to these communities.
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 stateof-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 codebase1 and benchmark2 are linked below.
SymbolicAI: A Neuro-Symbolic Perspective on Large Language Models (LLMs)
Overview
SymbolicAI is a framework that leverages machine learning, specifically Large Language Models (LLMs), as its foundation and composes operations based on task-specific prompting. Our approach adopts a divide-and-conquer strategy to break down complex problems into smaller, more manageable tasks. By reassembling these operations, we can solve intricate problems efficiently.Read full paper here.
Key Features
Seamless transition between differentiable and classical programmingNeuro-symbolic computation using LLMs
Composable operations for complex problem-solving
Integration with various engines (OpenAI, WolframAlpha, OCR, etc.)
Support for multimodal inputs and outputs
