Bridging Auxiliary Constraints to Resolve Instruction Following in Large Reasoning Models
Transactions of the Association for Computational Linguistics · 01.07.2026 · 14 · 1329-1347
DOI: 10.1162/tacl.a.730 ↗Kurz gefasst
Fachartikel in der Zeitschrift Transactions of the Association for Computational Linguistics, online erschienen am 01.07.2026. Verfasst von Zhengyi Zhao und 9 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Large Reasoning Models (LRMs) have demonstrated impressive capabilities in many tasks, yet they struggle with reliably following multiple instructions, either by failing to satisfy individual constraints or by struggling to balance competing constraints simultaneously. We formalize this challenge as the Constraint Adherence Problem (CAP). This paper introduces a novel framework that addresses CAP by representing instructions as a structured knowledge graph of constraints. Our approach, Constraint Relationship Graph Completion (CRGC), explicitly models relationships between constraints, identifies adherence challenges, and discovers “bridge constraints” that help the model better focus on and reconcile requirements. Bridge constraints act as auxiliary instructions that make primary constraints more salient and compatible. Unlike existing approaches that enhance instruction following through general training methods, CRGC specifically improves constraint satisfaction by leveraging the model’s own knowledge to create better pathways for generation. Experiments across three popular instruction following datasets demonstrate that our approach reduces constraint violations by 39% compared to standard prompting while maintaining reasoning abilities of large reasoning models.
Zitieren
APA
Zhao, Z., Zhang, S., Wang, H., Wang, Z., Zhao, Y., Zheng, Y., Li, B., He, Y., Wong, K., & Wu, X. (2026). Bridging Auxiliary Constraints to Resolve Instruction Following in Large Reasoning Models. Transactions of the Association for Computational Linguistics, 14, 1329-1347. https://doi.org/10.1162/tacl.a.730
Vancouver
Zhao Z, Zhang S, Wang H, Wang Z, Zhao Y, Zheng Y, et al. Bridging Auxiliary Constraints to Resolve Instruction Following in Large Reasoning Models. Transactions of the Association for Computational Linguistics. 2026;14:1329-1347. doi:10.1162/tacl.a.730
BibTeX
@article{Zhao2026,
author = {Zhao, Zhengyi and Zhang, Shubo and Wang, Huimin and Wang, Zezhong and Zhao, Yutian and Zheng, Yefeng and Li, Binyang and He, Yulan and Wong, Kam-Fai and Wu, Xian},
title = {Bridging Auxiliary Constraints to Resolve Instruction Following in Large Reasoning Models},
journal = {Transactions of the Association for Computational Linguistics},
year = {2026},
volume = {14},
pages = {1329--1347},
doi = {10.1162/tacl.a.730}
}
EUVIMED