LARFT: Closing the Cognition-Action Gap for Length Instruction Following in Large Language Models

Computer Science > Computation and Language [Submitted on 25 Feb 2026] LARFT: Closing the Cognition-Action Gap for Length Instruction Following in Large Language Models Wei Zhang, Lintong Du, Yuanhe Zhang, Zhenhong Zhou, Kun Wang, Li Sun, Sen Su Despite the strong performance of Large Language Models (LLMs) on complex instruction-following tasks, precise control of output length remains a persistent challenge. Existing methods primarily attempt to enforce length constraints by externally imposing length signals or optimization objectives, while largely overlooking the underlying limitation: the model's intrinsic deficit in length cognition. To address this, we propose LARFT (Length-Aware Reinforcement Fine-Tuning), a training framework that aligns the model's length cognition with its action. Specifically, LARFT integrates length-oriented reinforcement learning with a hindsight length awareness. By transforming on-policy data into hindsight self-awareness tasks where the model learns to identify the actual length of its own generation, LARFT jointly optimizes the model's internal representation of length information and refines its policy to satisfy length constraints, thereby achieving precise and reliable length instruction following. Extensive experiments across four base models demonstrate that LARFT outperforms existing baselines, achieving an average improvement of +20.92 points across three length instruction following benchmarks with only a marginal decline of -1.45 points on four general capability benchmarks. Comments: 19 pages, 6 figures Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI) Cite as: arXiv:2603.19255 [cs.CL]   (or arXiv:2603.19255v1 [cs.CL] for this version)   https://doi.org/10.48550/arXiv.2603.19255 Focus to learn more Submission history From: Wei Zhang [view email] [v1] Wed, 25 Feb 2026 15:34:21 UTC (5,634 KB) Access Paper: view license Current browse context: cs.CL < prev   |   next > new | recent | 2026-03 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)