Proceedings

Enhancing the Logical Reasoning Abilities of Large Language Models

Fengxiang Cheng

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Doctoral Consortium. Pages 10969-10970.

https://doi.org/10.24963/ijcai.2025/1239

Keywords

  • Natural Language Processing: NLP: Language models
  • Knowledge Representation and Reasoning: KRR: Applications
  • Machine Learning: ML: Neuro-symbolic methods
  • Knowledge Representation and Reasoning: KRR: Learning and reasoning

Abstract

Large language models (LLMs) have demonstrated impressive progress in various natural language progress tasks. However, it has been observed that LLMs still struggle with complex causal and logical reasoning. To facilitate this research direction, we first proposed a training method to distinguish causal relationships from spurious correlations in sentiment classification tasks. Then we conducted a comprehensive survey categorizing existing approaches, firstly identifying the main challenges of complex logical question-answering tasks and logical inconsistency across different questions. Our ongoing projects mainly focus on two points: (1) incorporating modal and epistemic logic to evaluate and enhance LLMs’ reasoning ability to handle more complex and diverse reasoning tasks, and (2) phased training LLMs with curriculum learning to improve their logical reasoning performance.

Fengxiang Cheng. 2025. Enhancing the Logical Reasoning Abilities of Large Language Models. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 10969–10970. https://doi.org/10.24963/ijcai.2025/1239
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards