Llama-Clin-REACT-70B

Model name in the manuscript: Clin-REACT 70B
Base model: meta-llama/Llama-3.3-70B-Instruct
Release format: merged full-parameter checkpoint

Built with Llama.

Clin-REACT is a family of large language models fine-tuned for clinical reasoning using the ICU-REACT framework. The models are designed to reason over clinically relevant information and produce responses for tasks spanning ICU decision-making and broader clinical-reasoning benchmarks.

This repository contains the merged, self-contained checkpoint. The LoRA adapter used during supervised fine-tuning has been merged into the corresponding base-model weights for distribution and inference.

Benchmark results

Clin-REACT 70B is compared with its Llama 3.3 70B Instruct backbone and selected open medical models at the 70B scale.

Scores below are the mean primary benchmark scores, reported as percentages. Higher is better. The macro average is the unweighted mean of the five benchmark primary scores. Bold indicates the best result within the comparison set shown for each benchmark.

The benchmarks contain 71 ICU-REACT cases, 174 SCT-Bench cases, 72 ER-Reason cases, 1,254 MedRBench cases, and 934 VivaBench cases. Because the benchmarks use different task formulations and primary scoring procedures, individual benchmark scores should primarily be interpreted within each benchmark.

Installation

pip install -U torch transformers accelerate

Load and use the model

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

MODEL_ID = "macontreras98/Llama-Clin-REACT-70B"

tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
model = AutoModelForCausalLM.from_pretrained(
    MODEL_ID,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

# Example ICU-REACT-style clinical reasoning sample
messages = [
    {
        "role": "system",
        "content": (
            "You are an ICU clinician. Write one coherent paragraph explaining "
            "which variables are most relevant to the decision and why."
        ),
    },
    {
        "role": "user",
        "content": (
            "Patient context: 75-year-old female ICU patient with recurrent high "
            "fevers and no clear infection source.\n\n"
            "Decision question: Is the frequency and severity of fever in this "
            "patient worrisome for ongoing infection or non-infectious etiology?"
        ),
    },
]

inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device)

with torch.inference_mode():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        do_sample=False,
    )

generated_tokens = outputs[0][inputs["input_ids"].shape[-1]:]
response = tokenizer.decode(
    generated_tokens,
    skip_special_tokens=True,
)

print(response)

For exact benchmark reproduction, use the same prompting, chat template, preprocessing, and decoding configuration used in the ICU-REACT evaluation pipeline.

Intended use and limitations

Clin-REACT is released for research on clinical reasoning and medical AI. It is not a medical device and should not be used as a substitute for professional clinical judgment, diagnosis, treatment decisions, or other autonomous patient-care decisions.

Benchmark performance does not establish clinical safety, prospective effectiveness, or suitability for deployment. Users are responsible for evaluating the model for their own setting and for complying with applicable privacy, security, institutional, and regulatory requirements.

License

This model is a derivative of Llama 3.3 70B Instruct and is distributed subject to the Llama 3.3 Community License Agreement and the corresponding Acceptable Use Policy. See the LICENSE and NOTICE files distributed with this repository.

The required attribution notice for the Llama materials should be retained in the repository NOTICE file.

Citation

If you use Clin-REACT in your research, please cite the associated ICU-REACT / Clin-REACT manuscript.

@article{contreras2026icureact,
  title   = {Teaching LLMs How ICU Physicians Approach Clinical Reasoning Through OMOP-Aligned Retrieval Improves Reasoning Across Clinical Domains},
  author  = {Contreras, Miguel and Siegel, Scott and Nerella, Subhash and Sena, Jessica and Zhang, Jiaqing and
             Sun, Heng and Akkaladevi, Hruday Tej and Lu, Peiyu and Rosen, Jordan and Kapoor, Sumit and
             Desaraju, Sasank and Thompson, Grace R. and Purcell, Jacob and Petrauskis, Michael and
             Hong, Philip KW and Brennan, Meghan and Chrabaszcz, Sarah and Smith, Tierra and Ren, Ronnie and
             Kabbash, Michel S. and Haziroglu, Ceyhun and Patel, Rushi and Gomez, Gabriel and Chaiklin, Charlotte and
             Leung, Randy and John, Kenneth N. and Wiggins, Whitman and Kayser, Philip and Bird, Vincent and
             Bruzzone, Maria and Loftus, Tyler J. and Bihorac, Azra and Rashidi, Parisa},
  journal = {arXiv preprint arXiv:2608.22622},
  year    = {2026},
  doi     = {10.48550/arXiv.2608.22622},
  url     = {https://arxiv.org/abs/2608.22622}
}