The paper introduces SafeMed-R1, a clinically audited LLM that significantly improves safety and ethical alignment for medical applications, matching or exceeding resident performance on safety-critic…

This paper evaluates multiple LLMs (DeepSeek-R1, OpenBioLLM-Llama3, Qwen 3.5) for generating privacy-safe, high-quality synthetic mental health reports, demonstrating their effectiveness in expanding…

The paper introduces LLMSurgeon, a framework that estimates the domain-level data mixture of a Large Language Model (LLM) using only generated text, thereby providing a post-hoc method to audit the mo…

The paper introduces MedCase-Structured, a synthetic, FHIR-formatted dataset designed to benchmark diagnostic reasoning in realistic EHR settings, showing that LLMs perform worse on structured data th…

The paper introduces a supervised fine-tuning pipeline using large language models to accurately categorize sentence-level clinical provenance across multi-disciplinary hospital notes, demonstrating t…

The paper introduces MIRA, a bilingual benchmark that reveals that LLMs tend to dilute or omit critical medical information when responding to prompts from users with low health literacy, a pattern te…

The paper investigates apparent LLM triage failures and concludes that the errors originate in the output format and decision process, rather than a deficiency in the model's underlying clinical knowl…

This paper introduces KliniskVestBERT, a suite of BERT models specialized by pre-training on a large, diverse corpus of real-world Norwegian clinical texts, demonstrating superior performance for clin…

The paper proposes a debiasing fine-tuning technique to efficiently enhance the robustness of Large Language Models against semantically similar but textually altered prompts.

The authors demonstrate that fine-tuning a two-stage retrieval system using synthetic data generated by large language models can significantly improve the performance of medical semantic search for c…

The study demonstrates that LLMs exhibit significant, language-driven disparities in medical triage recommendations, recommending emergency care more frequently for English and Arabic prompts, even wh…

HypothesisMed introduces an inference-time pipeline for biomedical question answering that improves model reliability and structured output generation by fusing multiple model outputs and diagnosing t…

The paper proposes 'Think Fast, Talk Smart,' a pipeline that separates deterministic data analysis from LLM generation, showing that offloading recurring, structured tasks to code significantly improv…

The paper proposes Shapley-based input uncertainty Quantification (ShaQ), a novel framework that uses Shapley values to precisely attribute input-induced uncertainty to specific spans of text, providi…

The paper introduces Reverse Probing, a novel framework that quantifies token-level uncertainty in large language models (LLMs) specifically for clinical text by analyzing internal model activations,…

The paper introduces EHRBench, a large-scale, automated, and reliable benchmark derived from real Electronic Health Records (EHRs) to rigorously evaluate the clinical decision-making capabilities of L…

The paper proposes Sensitivity-Uncertainty Alignment (SUA), a framework that measures the misalignment between a model's prediction instability and its stated uncertainty to improve model reliability.

The paper demonstrates that increasing the toxicity of prompts significantly degrades the factual reliability of LLMs, a degradation linked to the selective amplification of perturbation-sensitive nod…

This paper investigates why self-harm prediction models struggle to generalize across different hospitals, finding that variations in local lexical expression and feature importance are the primary ca…

This paper introduces the concept of Safety Geometry Collapse, demonstrating that multimodal inputs degrade the safety separation of LLMs, and proposes ReGap, a training-free method that adaptively co…