
Jaeyong Ko, Pilsung Kang, Yukyung Lee
arXiv preprint arXiv:2606.25524 2026
Identifies single-token triggers that can sharply change the success or failure of LLM mathematical reasoning, supporting fine-grained analysis of reasoning reliability.
Jaeyong Ko, Pilsung Kang, Yukyung Lee
arXiv preprint arXiv:2606.25524 2026
Identifies single-token triggers that can sharply change the success or failure of LLM mathematical reasoning, supporting fine-grained analysis of reasoning reliability.