Supervised Fine-tuning with Synthetic Rationale Data Hurts Real-World Disease Prediction

Computer Science > Artificial Intelligence [Submitted on 9 Jun 2026] Supervised Fine-tuning with Synthetic Rationale Data Hurts Real-World Disease Prediction Buxin Su, Bingxuan Li, Cheng Qian, Yiwei Wang, Jin Jin, Bingxin Zhao Supervised fine-tuning with synthetic rationale data is widely assumed to improve language model performance on clinical prediction tasks by teaching models not just what to predict but why. We test this assumption on five-year Alzheimer's disease and related dementias (ADRD) prediction from longitudinal health histories. Across a large-scale controlled experiment of 504 configurations, we find that rationale-based SFT consistently and substantially hurts prediction performance relative to label-only fine-tuning. The degradation persists across model families and data scales, and is not resolved by using a reasoning-oriented base model. Crucially, the failure is not explained by poor rationale quality: human expert annotation confirms that the generated rationales are medically accurate and faithfully grounded in patient-specific evidence, and few-shot experiments show that the same rationales improve performance when used as inference-time demonstrations rather than training targets. We identify the root cause as a structural conflict between narrative plausibility and discriminative optimization. We hope our work paves the path toward a more precise understanding of when and how rationale-based supervision helps and when it does not, guiding the responsible development of language models for high-stakes clinical prediction. Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG) Cite as: arXiv:2606.10279 [cs.AI]   (or arXiv:2606.10279v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.10279 Focus to learn more Submission history From: Buxin Su [view email] [v1] Tue, 9 Jun 2026 01:00:04 UTC (1,104 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.CL cs.LG 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?)