The study investigates how post‑training alignment techniques affect small language models (SLMs) for generating medication leaflets from structured biomedical data. Four alignment methods—supervised fine‑tuning (SFT), direct preference optimization (DPO), odds ratio preference optimization (ORPO), and group relative policy optimization (GRPO)—are evaluated using Qwen‑2.5 models, with a new FDALeaflets dataset derived from OpenFDA drug labels for zero‑shot cross‑regulatory testing. Results show that aligned SLMs can outperform GPT‑5 on reference‑based metrics, while ORPO and GRPO achieve the highest semantic textual similarity scores in‑domain and on FDALeaflets, respectively, highlighting the importance of alignment for semantic fidelity and generalization.
arXiv:2511.21075v4 Announce Type: replace-cross Abstract: Engineering LLMs to accelerate life sciences research requires a robust alignment with biomedical knowledge. We observe that biomedical text...
arXiv:2604.26766v2 Announce Type: replace-cross Abstract: Accurate and consistent Emergency Severity Index (ESI) assignment remains a persistent challenge in emergency departments, where highly varia...
arXiv:2606. 18703v1 Announce Type: new Abstract: Pretrained biological language models expose per-token probability distributions through masked-token prediction, providing the likelihood interface central to sequence design, variant scoring, and mechanistic interpretation.
arXiv:2606. 12590v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have achieved strong performance across medical imaging tasks, yet they remain prone to factual inconsistencies, poor visual grounding, and misalignment with clinically meaningful feedback.
arXiv:2608. 19825v1 Announce Type: cross Abstract: Medical image captioning is a technique that accelerates early-stage diagnostic workflows and enhances the interpretability of medical diagnostic AI systems.
This study benchmarks transformer models for Bangla medical named entity recognition (NER), comparing BanglaBERT, multilingual BERT (mBERT), XLM‑RoBERTa, and GPT‑4o mini under zero‑shot and few‑shot prompting. Across a full test set of 3,179 samples, fine‑tuned XLM‑RoBERTa achieves a new state‑of‑the‑art F1‑score of 0.5959, while BanglaBERT lags with 0.4937, suggesting that domain diversity outweighs language specificity. The analysis shows high performance on Medicine and Specialist entities (F1 > 0.83) but lower accuracy on Symptoms (F1 0.4367), and demonstrates that fine‑tuned transformers outperform prompt‑only approaches by a factor of 3.76.
arXiv:2510. 17532v2 Announce Type: replace-cross Abstract: Predicting cancer treatment outcomes requires models that are both accurate and interpretable, particularly in the presence of heterogeneous clinical data.
CliQ‑RRG is a two‑stage framework for generating radiology reports that aligns visual and textual data using disease‑aware embeddings and prior‑guided attention to capture multi‑view dependencies. The second stage retrieves graph‑grounded clinical evidence and employs a large language model to produce concise, interpretable question‑answer style reports with diagnostic summaries. Experiments on two chest X‑ray benchmarks show that CliQ‑RRG outperforms previous methods on both lexical and clinical metrics, producing accurate and clinically coherent reports.
Neurosymbolic Alignment couples a 7B clinical language model with a graph‑based physiological world model to score candidate responses using homeostatic constraints, multi‑hop plausibility, and drug‑interaction penalties. This training‑time framework drives iterative on‑policy updates and achieves a 90.8% Clinical Safety Score on the CSB benchmark, outperforming ORPO, GPT‑4 (5‑shot), and a self‑correction pipeline. Ablation studies show that the HGNN scoring and iterative training are the key contributors to the safety gains.
arXiv:2605. 04539v4 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO), the efficient alternative to PPO-based RLHF, falls short on knowledge-intensive generation: standard preference signals from human annotators or LLM judges exhibit a systematic verbosity bias that rewards fluency over logical correctness.
The paper introduces a unified framework for aligning biomedical text with knowledge graphs using a lightweight projection learned via contrastive learning, keeping the text encoder and KG embedding model frozen. It evaluates six design choices—text encoder, KG embedding, projection head, triple composition, training direction, and hard‑negative sampling—on a newly created CTD‑Align corpus of 22K chemical‑gene interaction pairs linked to PubMed passages. The study finds that triple composition and training direction have the largest impact, while simpler linear projections over concatenated subject, predicate, and object embeddings yield the best performance.
CliQ‑RRG is a two‑stage framework for generating radiology reports that aligns visual and textual data using disease‑aware embeddings and a Prior‑Guided Attention Module to capture multi‑view dependencies. In the second stage, GraphRAG‑guided retrieval adds graph‑grounded clinical evidence, and a large language model restructures the content into concise question‑answer pairs with diagnostic summaries. Experiments on two chest X‑ray benchmarks show that CliQ‑RRG outperforms previous methods in both lexical and clinical metrics, producing accurate and clinically coherent QA‑style reports.