Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Text
This addresses the need for more reliable and general reasoning systems in AI, particularly for NLP and robotics applications, by combining LLMs with formal logic, though it is incremental as it builds on existing methods.
The study tackled the problem of limited reasoning ability in large language models (LLMs) by coupling them with logic programming, specifically answer set programs, to create a robust system for question-answering tasks without retraining. The result was state-of-the-art performance on benchmarks like bAbI, StepGame, CLUTRR, and gSCAN, and successful handling of robot planning tasks that LLMs alone failed.
While large language models (LLMs), such as GPT-3, appear to be robust and general, their reasoning ability is not at a level to compete with the best models trained for specific natural language reasoning problems. In this study, we observe that a large language model can serve as a highly effective few-shot semantic parser. It can convert natural language sentences into a logical form that serves as input for answer set programs, a logic-based declarative knowledge representation formalism. The combination results in a robust and general system that can handle multiple question-answering tasks without requiring retraining for each new task. It only needs a few examples to guide the LLM's adaptation to a specific task, along with reusable ASP knowledge modules that can be applied to multiple tasks. We demonstrate that this method achieves state-of-the-art performance on several NLP benchmarks, including bAbI, StepGame, CLUTRR, and gSCAN. Additionally, it successfully tackles robot planning tasks that an LLM alone fails to solve.