Derailer-Rerailer: Adaptive Verification for Efficient and Reliable Language Model Reasoning

Guangya Wan, Yuqi Wu, Hao Wang, Shengming Zhao, Jie Chen, Sheng Li


Abstract
Large Language Models (LLMs) have shown impressive reasoning capabilities, yet existing prompting methods face a critical trade-off: simple approaches often struggle with complex tasks and reasoning stability, while more sophisticated methods require multiple inferences and substantial computational resources, limiting their practical deployment. To address this challenge, we propose Derailer-Rerailer, a novel framework that adaptively balances reasoning accuracy and computational efficiency. At its core, our framework employs a lightweight Derailer mechanism to assess reasoning stability and selectively triggers an advanced Rerailer verification process only when necessary, thereby optimizing computational resource usage. Extensive evaluation across both open and closed-source models on more than 20 categories of mathematical, symbolic, and commonsense reasoning tasks demonstrates our framework’s effectiveness: Derailer-Rerailer achieves significant accuracy improvements (8-11% across various reasoning tasks) while maintaining 2-3 times better efficiency than existing verification methods, with particularly strong performance in mathematical and symbolic reasoning, offering a practical solution for enhancing LLM reasoning reliability while significantly reducing computational overhead.
Anthology ID:
2025.findings-acl.18
Volume:
Findings of the Association for Computational Linguistics: ACL 2025
Month:
July
Year:
2025
Address:
Vienna, Austria
Editors:
Wanxiang Che, Joyce Nabende, Ekaterina Shutova, Mohammad Taher Pilehvar
Venues:
Findings | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
327–348
Language:
URL:
https://preview.aclanthology.org/ingestion-acl-25/2025.findings-acl.18/
DOI:
Bibkey:
Cite (ACL):
Guangya Wan, Yuqi Wu, Hao Wang, Shengming Zhao, Jie Chen, and Sheng Li. 2025. Derailer-Rerailer: Adaptive Verification for Efficient and Reliable Language Model Reasoning. In Findings of the Association for Computational Linguistics: ACL 2025, pages 327–348, Vienna, Austria. Association for Computational Linguistics.
Cite (Informal):
Derailer-Rerailer: Adaptive Verification for Efficient and Reliable Language Model Reasoning (Wan et al., Findings 2025)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-acl-25/2025.findings-acl.18.pdf