Arithmetic Reasoning with LLM: Prolog Generation & Permutation
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:GJFIT6CCrecord.jsonopen to challenge →
read the original abstract
Instructing large language models (LLMs) to solve elementary school math problems has shown great success using Chain of Thought (CoT). However, the CoT approach relies on an LLM to generate a sequence of arithmetic calculations which can be prone to cascaded calculation errors. We hypothesize that an LLM should focus on extracting predicates and generating symbolic formulas from the math problem description so that the underlying calculation can be done via an external code interpreter. We investigate using LLM to generate Prolog programs to solve mathematical questions. Experimental results show that our Prolog-based arithmetic problem-solving outperforms CoT generation in the GSM8K benchmark across three distinct LLMs. In addition, given the insensitive ordering of predicates and symbolic formulas in Prolog, we propose to permute the ground truth predicates for more robust LLM training via data augmentation.
This paper has not been read by Pith yet.
Forward citations
Cited by 1 Pith paper
-
Autonomous Business System via Neuro-symbolic AI
AUTOBUS is a neuro-symbolic architecture that uses AI agents to generate executable logic programs from business instructions and knowledge graphs for end-to-end process automation with human supervision.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.