Evaluation of 22 LLMs shows they are more susceptible to spin in medical abstracts than humans but can recognize and mitigate it when prompted.
Alpacare: Instruction-tuned large language models for medical application
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
fields
cs.CL 7representative citing papers
Creates the first bilingual clinical benchmark from Brazilian cases and reports that English performance advantage exists only in diagnosis retrieval, disappearing in the other three tasks.
Exclusive Unlearning makes LLMs safe by forgetting all but retained domain knowledge, protecting against jailbreaks while preserving useful responses in areas like medicine and math.
TRACE is a taxonomy-grounded synthetic instruction-tuning dataset with 2,999 examples for ABA teaching-program generation and multi-session behavioral interpretation, released with code, provenance, and stratified splits.
A 14B model trained on synthetic data from Brazilian clinical guidelines outperforms larger LLMs on new benchmarks for Brazilian healthcare protocols.
RAG-adapted LLaMA-3-8B outperforms both baseline and fine-tuned models on expert-rated accuracy (75.5%), relevance (90.8%), and overall preference (85.2%) for additive manufacturing questions.
A comprehensive survey of knowledge distillation for LLMs structured around algorithms, skill enhancement, and vertical applications, highlighting data augmentation as a key enabler.
citing papers explorer
-
Caught in the Web of Words: Do LLMs Fall for Spin in Medical Literature?
Evaluation of 22 LLMs shows they are more susceptible to spin in medical abstracts than humans but can recognize and mitigate it when prompted.
-
Beyond English benchmarks: clinical llm evaluation in Brazilian Portuguese
Creates the first bilingual clinical benchmark from Brazilian cases and reports that English performance advantage exists only in diagnosis retrieval, disappearing in the other three tasks.
-
Exclusive Unlearning
Exclusive Unlearning makes LLMs safe by forgetting all but retained domain knowledge, protecting against jailbreaks while preserving useful responses in areas like medicine and math.
-
TRACE: A taxonomy-grounded synthetic dataset for teaching-program generation and session interpretation in Applied Behavior Analysis
TRACE is a taxonomy-grounded synthetic instruction-tuning dataset with 2,999 examples for ABA teaching-program generation and multi-session behavioral interpretation, released with code, provenance, and stratified splits.
-
Teaching LLMs Brazilian Healthcare: Injecting Knowledge from Official Clinical Guidelines
A 14B model trained on synthetic data from Brazilian clinical guidelines outperforms larger LLMs on new benchmarks for Brazilian healthcare protocols.
-
Domain Adaptation of Large Language Models for Polymer-Composite Additive Manufacturing Using Retrieval-Augmented Generation and Fine-Tuning
RAG-adapted LLaMA-3-8B outperforms both baseline and fine-tuned models on expert-rated accuracy (75.5%), relevance (90.8%), and overall preference (85.2%) for additive manufacturing questions.
-
A Survey on Knowledge Distillation of Large Language Models
A comprehensive survey of knowledge distillation for LLMs structured around algorithms, skill enhancement, and vertical applications, highlighting data augmentation as a key enabler.