Interpreting Arithmetic Reasoning in Large Language Models using Game-Theoretic Interactions
Published in NeurIPS, 2025
Recommended citation: Wen, L., Zheng, L., Li, H., Sun, L., Wei, Z., & Shen, W. Interpreting Arithmetic Reasoning in Large Language Models using Game-Theoretic Interactions. In NeurIPS 2025. https://openreview.net/pdf?id=tRvzEL64dY
Abstract. This paper interprets arithmetic reasoning in large language models using game-theoretic interactions, quantifying interaction patterns encoded during forward propagation to explain how LLMs solve arithmetic problems.
Authors: Leilei Wen, Liwei Zheng, Hongda Li, Lijun Sun, Zhihua Wei*, Wen Shen†.
Recommended citation: Wen, L., Zheng, L., Li, H., Sun, L., Wei, Z., & Shen, W. Interpreting Arithmetic Reasoning in Large Language Models using Game-Theoretic Interactions. In NeurIPS 2025.