Can We Steer Reasoning Direction by Thinking Intervention?

Xingsheng Zhang, Luxi Xing, Chen Zhang, Yanbing Liu, Yifan Deng, Yunpeng Li, Yue Hu, Chenxu Niu


Abstract
Large Reason Models (LRMs) extend long reasoning process to solve complex tasks. However, due to the lack of fine-grained control, they often suffer from overthinking and erroneous reasoning problems, risking accuracy loss. To address this issue, we introduce Reasoning Direction Steering (RDS) to enable fine-grained control over LRMs’ reasoning behaviors by aligning reasoning trajectories with specific cognitive patterns. We develop a simple yet effective paradigm, Thinking Intervention, which explores two key dimensions - intervention positions and intervention styles - to achieve integration intervention throughout model reasoning processes. To validate the effectiveness of our approach, we conduct comprehensive experiments on multi-hop question answering tasks using state-of-the-art LRMs, including Qwen3-Series and R1-Series models. Experimental results demonstrate the efficacy of Thinking Intervention with 9.4% average improvement on R1-Series models and 1.9% improvement on Qwen3-Series models.
Anthology ID:
2025.findings-emnlp.209
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3888–3913
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.209/
DOI:
Bibkey:
Cite (ACL):
Xingsheng Zhang, Luxi Xing, Chen Zhang, Yanbing Liu, Yifan Deng, Yunpeng Li, Yue Hu, and Chenxu Niu. 2025. Can We Steer Reasoning Direction by Thinking Intervention?. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 3888–3913, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Can We Steer Reasoning Direction by Thinking Intervention? (Zhang et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.209.pdf
Checklist:
 2025.findings-emnlp.209.checklist.pdf