Parameter-Efficient Conciseness Adaptation: Differentiable Length Control for Concise Clinical Reasoning in Smaller Language Models
cs.CL, cs.AI
Submitted: 2026-11-12
Updated: 2026-11-12
Code: https://github.com/tanzeelabbas/PECA-Medical
Terminology
Sources
- LoRA: Low-Rank Adaptation of Large Language Models
- A Comparative Analysis of Instruction Fine-Tuning LLMs for Financial Text Classification
- QLoRA: Efficient Finetuning of Quantized LLMs
- Fine-tuning Smaller Language Models for Question Answering over Financial Documents
- Length-Controlled Margin-Based Preference Optimization without Reference Model
- Qwen3 Technical Report
- Step-by-Step Unmasking for Parameter-Efficient Fine-tuning of Large Language Models
- Controlling Summarization Length Through EOS Token Weighting
- SimPO: Simple Preference Optimization with a Reference-Free Reward
- Disentangling Length from Quality in Direct Preference Optimization
- HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs
- SmartThinker: Progressive Chain-of-Thought Length Calibration for Efficient Large Language Model Reasoning
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