When Domain Pretraining Interferes with Instruction Alignment: An Empirical Study of Adapter Merging in Medical LLMs
When Domain Pretraining Interferes with Instruction Alignment: An Empirical Study of Adapter Merging in Medical LLMs explores Improving medical LLMs with adapter interference strategies to better align domain knowledge and instruction-following capabilities.. Commercial viability score: 3/10 in Medical AI.
BUILDER'S SANDBOX
Build This Paper
Use an AI coding agent to implement this research.
OpenAI CodexAI Agent
Lightweight coding agent in your terminal.
Claude CodeAI Agent
Agentic coding tool for terminal workflows.
AntiGravity IDEScaffolding
AI agent mindset installer and workflow scaffolder.
CursorIDE
AI-first code editor built on VS Code.
VS CodeIDE
Free, open-source editor by Microsoft.
Recommended Stack
Startup Essentials
Estimated $9K - $13K over 6-10 weeks.
See exactly what it costs to build this -- with 3 comparable funded startups.
7-day free trial. Cancel anytime.
Discover the researchers behind this paper and find similar experts.
7-day free trial. Cancel anytime.
Related Papers
- Prior WorkLanguage-Pretraining-Induced Bias: A Strong Foundation for General Vision TasksViability: 3.0
- Higher ViabilityCountering Catastrophic Forgetting of Large Language Models for Better Instruction Following via Weight-Space Model MergingViability: 7.0
- Higher ViabilityMerge and Conquer: Instructing Multilingual Models by Adding Target Language WeightsViability: 5.0
- Higher ViabilityACE-LoRA: Graph-Attentive Context Enhancement for Parameter-Efficient Adaptation of Medical Vision-Language ModelsViability: 9.0
- Higher Viability