Multi-step Inference over Unstructured Data
This addresses the need for reliable AI in critical domains, but it appears incremental as it builds on existing neuro-symbolic approaches.
The paper tackles the problem of achieving precision and logical consistency in high-stakes decision-making tasks like medical, legal, and finance, where pure LLM or RAG methods often fail, by developing a neuro-symbolic AI platform called Cora that integrates fine-tuned LLMs with symbolic reasoning, resulting in superior performance compared to baselines.
The advent of Large Language Models (LLMs) and Generative AI has revolutionized natural language applications across various domains. However, high-stakes decision-making tasks in fields such as medical, legal and finance require a level of precision, comprehensiveness, and logical consistency that pure LLM or Retrieval-Augmented-Generation (RAG) approaches often fail to deliver. At Elemental Cognition (EC), we have developed a neuro-symbolic AI platform to tackle these problems. The platform integrates fine-tuned LLMs for knowledge extraction and alignment with a robust symbolic reasoning engine for logical inference, planning and interactive constraint solving. We describe Cora, a Collaborative Research Assistant built on this platform, that is designed to perform complex research and discovery tasks in high-stakes domains. This paper discusses the multi-step inference challenges inherent in such domains, critiques the limitations of existing LLM-based methods, and demonstrates how Cora's neuro-symbolic approach effectively addresses these issues. We provide an overview of the system architecture, key algorithms for knowledge extraction and formal reasoning, and present preliminary evaluation results that highlight Cora's superior performance compared to well-known LLM and RAG baselines.