REVIEW 13 cited by
PMC-LLaMA: Towards Building Open-source Language Models for Medicine
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Recently, Large Language Models (LLMs) have showcased remarkable capabilities in natural language understanding. While demonstrating proficiency in everyday conversations and question-answering situations, these models frequently struggle in domains that require precision, such as medical applications, due to their lack of domain-specific knowledge. In this paper, we describe the procedure for building a powerful, open-source language model specifically designed for medicine applications, termed as PMC-LLaMA. Our contributions are threefold: (i) we systematically investigate the process of adapting a general-purpose foundation language model towards medical domain, this involves data-centric knowledge injection through the integration of 4.8M biomedical academic papers and 30K medical textbooks, as well as comprehensive fine-tuning for alignment with domain-specific instructions; (ii) we contribute a large-scale, comprehensive dataset for instruction tuning. This dataset encompasses medical question-answering (QA), rationale for reasoning, and conversational dialogues, comprising a total of 202M tokens; (iii) we conduct thorough ablation studies to demonstrate the effectiveness of each proposed component. While evaluating on various public medical question-answering benchmarks, our lightweight PMCLLaMA, which consists of only 13 billion parameters, exhibits superior performance, even surpassing ChatGPT. All models, codes, datasets can be found in https://github.com/chaoyi-wu/PMC-LLaMA.
Forward citations
Cited by 13 Pith papers
-
Facts Fade Fast: Evaluating Memorization of Outdated Medical Knowledge in Large Language Models
LLMs more often reproduce older medical conclusions than updated ones, as shown by a new 512-question dataset of Cochrane reviews whose verdicts changed over time.
-
WisWheat: A Three-Tiered Vision-Language Dataset for Wheat Management
A new wheat-specific dataset with pretraining, quantitative, and instruction-tuning layers improves VLM performance on wheat stress diagnosis and growth-stage management tasks.
-
MedBookVQA: A Systematic and Comprehensive Medical Benchmark Derived from Open-Access Book
MedBookVQA is a new 5,000-question, textbook-derived multimodal benchmark for testing medical AI systems, with labels for imaging modality, body anatomy, and clinical specialty.
-
OntoTune: Ontology-Driven Self-training for Aligning Large Language Models
A self-training method that uses an existing medical ontology to select and learn from the model's own inconsistent answers improves medical QA and taxonomy tasks while preserving general ability.
-
Channel Merging: Preserving Specialization for Merged Experts
Channel Merging clusters similar channel parameters from fine-tuned LLMs and reconstructs the selected expert at inference, matching unmerged accuracy with about 53% of the ensemble's parameters.
-
TrimLLM: Progressive Layer Dropping for Domain-Specific LLMs
Progressive layer dropping during domain fine-tuning can halve an LLM's depth with small accuracy loss, yielding 2-5x throughput gains on consumer GPUs.
-
Ensuring Safety and Trust: Analyzing the Risks of Large Language Models in Medicine
MedGuard, a 1,000-question expert-verified benchmark, shows current medical LLMs lag human physicians on safety across fairness, privacy, robustness, resilience, and truthfulness.
-
GMAI-VL & GMAI-VL-5.5M: A Large Vision-Language Model and A Comprehensive Multimodal Dataset Towards General Medical AI
GMAI-VL-5.5M is a new 5.5M-sample medical image-text dataset built from 219 datasets via GPT-4o annotation-guided generation, and GMAI-VL is a three-stage LLaVA-style model reporting SOTA numbers, though the evaluatio...
-
JRadiEvo: A Japanese Radiology Report Generation Model Enhanced by Evolutionary Optimization of Model Merging
JRadiEvo shows that evolutionary model merging can adapt a vision-language model to generate Japanese chest X-ray reports using only 50 translated samples, beating larger baselines on ROUGE-L and METEOR.
-
CLUES: Collaborative High-Quality Data Selection for LLMs via Training Dynamics
A collaborative data-selection method that scores each private sample's influence on a public anchor set and filters by a global threshold before federated learning or model merging.
-
Balancing Knowledge Delivery and Emotional Comfort in Healthcare Conversational Systems
Fine-tuning a 1B medical chatbot on LLM-rewritten emotional dialogues improves its emotion scores with only small changes in n-gram overlap with the original medical responses.
-
Improving TCM Question Answering through Tree-Organized Self-Reflective Retrieval with LLMs
A tree-organized, self-reflective retrieval framework over a TCM knowledge base lifts GPT-4 accuracy on a 600-question licensing-exam sample by 19.85 absolute percentage points.
-
Open Foundation Models in Healthcare: Challenges, Paradoxes, and Opportunities with GenAI Driven Personalized Prescription
Open LLMs (LLaMA-2, LLaMA-3, Mistral, Meditron) roughly match GPT-4 on a 25-patient prescription-suitability check when given SmPC context via RAG, though some interaction classes degrade with RAG.
Discussion (0). Continue with ORCID to comment.