Guardrail Erosion in Domain Fine-Tuned Large Language Models: A Paired Audit of Knowledge-Centric Abstention in Biomedical LLMs
cs.CL, cs.AI
Submitted: 2026-11-05
Updated: 2026-11-05
Terminology
Sources
- On the Opportunities and Risks of Foundation Models
- HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs
- Med42 -- Evaluating Fine-Tuning Strategies for Medical LLMs: Full-Parameter vs. Parameter-Efficient Approaches
- Med42-v2: A Suite of Clinical LLMs
- Gemma 3 Technical Report
- The Llama 3 Herd of Models
- Measuring Massive Multitask Language Understanding
- MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning
- SciSafeEval: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Tasks
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
- MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering
- MedGemma Technical Report
- A StrongREJECT for Empty Jailbreaks
- Clinical Camel: An Open Expert-Level Medical Language Model with Dialogue-Based Knowledge Encoding
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Safety Measurements for Fine-tuned LLMs Should be Grounded in Capability
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data