mlsanityData to 7 Oct 2026

Exploring Post-Training Alignment of Small Language Models for Biomedical Data-to-Text Generation: A Case Study of Medication Leaflet

arXiv 2607.13430 ↗First posted 15 Jul 2026cs.CLcited by 0

On the map: LLM alignment / RLHF / preference optimisation → Medical LLM alignment

Abstract (arXiv)

Translating complex biomedical data into patient-friendly narratives is central to modern biomedical informatics. This study presents a comparative analysis of training small language models (SLMs) in specialized biomedical datato-text generation tasks. We explore widely adopted post-training methods including supervised fine-tuning (SFT), direct preference optimization (DPO), odds ratio preference optimization (ORPO), and group relative policy optimization (GRPO) with Qwen-based SLMs on a medicine package leaflets dataset. To assess cross-dataset generalizability, we also curated drug label data from openFDA. We evaluate models using both standard lexical overlap metrics like ROUGE as well as semantic similarity measures. Across our experiments, the results show that (1) the aligned SLMs outperform proprietary models like GPT-5; (2) ORPO outperforms the SFTbaselines; (3) GRPO yields the most robust cross-dataset performance among the alignment methods tested as well as GPT-5.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Medical LLM alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 14 of its 23 references that are in the map. First posted on arXiv 15 Jul 2026.

Builds on

14 of 23 references.

References · 14

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  4. 2024Qwen2.5 Technical Reportcited by 4,713
  5. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  6. 2025Understanding R1-Zero-Like Training: A Critical Perspectivecited by 1,276
  7. 2025Group Sequence Policy Optimizationcited by 788
  8. 2024ORPO: Monolithic Preference Optimization without Reference Modelcited by 556
  9. 2023Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessmentcited by 227
  10. 2024A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthinesscited by 125
  11. 2024Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimizationcited by 66
  12. 2024RS-DPO: A Hybrid Rejection Sampling and Direct Preference Optimization Method for Alignment of Large Language Modelscited by 48
2 more
  1. 2024Instruction Fine-Tuning: Does Prompt Loss Matter?cited by 26
  2. 2021Biomedical Data-to-Text Generation via Fine-Tuning Transformerscited by 9

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024A Survey for Large Language Models in Biomedicine
  2. 2024MedCare: Advancing Medical LLMs through Decoupling Clinical Alignment and Knowledge Aggregation
  3. 2025A Scoping Review of Synthetic Data Generation by Language Models in Biomedical Research and Application: Data Utility and Quality Perspectives
  4. 2025IIMedGPT: Promoting Large Language Model Capabilities of Medical Tasks by Efficient Human Preference Alignment
  5. 2024Unlocking Historical Clinical Trial Data with ALIGN: A Compositional Large Language Model System for Medical Coding
  6. 2024Biomedical Large Languages Models Seem not to be Superior to Generalist Models on Unseen Medical Data
  7. 2026Linguistically-Aligned and Visually-Grounded Preference Optimization for Clinically-Augmented Medical Report Generation
  8. 2025BALI: Enhancing Biomedical Language Representations through Knowledge Graph and Language Model Alignment