File size: 20,382 Bytes
129852c
 
 
 
 
 
 
 
 
 
 
 
 
5f79dea
 
 
 
 
 
 
129852c
a9a7e65
129852c
1096508
129852c
 
 
5f79dea
129852c
 
 
5f79dea
 
129852c
 
 
 
5f79dea
 
 
 
 
129852c
5f79dea
 
 
129852c
5f79dea
 
 
 
 
 
 
 
 
 
 
 
 
129852c
5f79dea
 
 
 
 
 
 
 
9a14a59
 
 
2350e39
 
9f8d38d
20a9992
 
57e5557
d046ce3
9a14a59
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2350e39
 
a6cdcb6
 
 
 
 
 
 
 
 
c77c689
a6cdcb6
2350e39
 
 
 
 
c77c689
2350e39
 
 
 
 
 
 
 
 
 
 
7f2419d
2350e39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25d48c7
2350e39
 
 
 
 
c9414c7
 
5290391
c9414c7
5290391
 
 
 
 
 
 
 
 
 
 
 
4f89ff1
2560a0f
4f89ff1
2350e39
 
 
 
 
 
 
 
bb4f6c0
2350e39
 
 
 
25d48c7
2350e39
 
 
 
 
 
25d48c7
2350e39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25d48c7
2350e39
 
 
 
 
 
 
 
 
 
 
 
 
 
25d48c7
2350e39
 
 
 
 
25d48c7
2350e39
 
 
 
 
 
 
 
 
 
bb4f6c0
2350e39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a6cdcb6
2350e39
616f15b
a6cdcb6
2350e39
9a14a59
2350e39
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
---
base_model: meta-llama/Meta-Llama-3-70B-Instruct
tags:
- llama-3
- llama
- Mixtral
- instruct
- finetune
- chatml
- DPO
- RLHF
- gpt4
- distillation
- heathcare
- medical
- clinical
- med
- lifescience
- Pharmaceutical
- Pharma
model-index:
- name: OpenBioLLM-70B
  results: []
license: llama3
language:
- en
widget:
- example_title: OpenBioLLM-70B
  messages:
  - role: system
    content: >-
      You are an expert and experienced from the healthcare and biomedical
      domain with extensive medical knowledge and practical experience.
  - role: user
    content: How long does it take for newborn jaundice to go away?
  output:
    text: >-
      Newborn jaundice, also known as neonatal jaundice, is a common condition
      in newborns where the yellowing of the skin and eyes occurs due to an
      elevated level of bilirubin in the blood. Bilirubin is a yellow pigment
      that forms when red blood cells break down. In most cases, newborn
      jaundice resolves on its own without any specific treatment.

      The duration of newborn jaundice can vary depending on several factors
      such as the underlying cause, gestational age at birth, and individual
      variations in bilirubin metabolism. Here are some general guidelines:

      1. Physiological jaundice: This is the most common type of newborn
      jaundice and usually appears within 24-72 hours after birth. It tends to
      peak between the second and fifth day of life and gradually improves over
      the next week or two. By the time the baby is one week old, the jaundice
      should have mostly resolved. 2. Breast milk jaundice: This type of
      jaundice occurs in breastfed babies and may appear later than
      physiological jaundice, typically between the fifth and fourteenth day of
      life. It tends to persist for a longer duration but usually resolves
      within six weeks after birth. 3. Pathological jaundice: This type of
      jaundice is less common and occurs due to an underlying medical condition
      that affects bilirubin metabolism or liver function. The duration of
      pathological jaundice depends on the specific cause and may require
      treatment.

      It's important for parents to monitor their newborn's jaundice closely and
      seek medical advice if the jaundice progresses rapidly, becomes severe, or
      is accompanied by other symptoms such as poor feeding, lethargy, or
      excessive sleepiness. In these cases, further evaluation and management
      may be necessary. Remember that each baby is unique, and the timing of
      jaundice resolution can vary. If you have concerns about your newborn's
      jaundice, it's always best to consult with a healthcare professional for
      personalized advice and guidance.
---


<div align="center">
<img width="260px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/BrQCb95lmEIFz79QAmoNA.png"></div>

![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/fJIOPJnY6Ff6fUiSIuMEt.png)




<div align="center">
  
  <h1>Advancing Open-source Large Language Models in Medical Domain</h1>
</div>

<p align="center" style="margin-top: 0px;">
  <a href="https://colab.research.google.com/drive/1F5oV20InEYeAJGmBwYF9NM_QhLmjBkKJ?usp=sharing">
    <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="OpenChat Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;"/>
    <span class="link-text" style=" margin-right: 5px;">Online Demo</span>
  </a> |
  <a href="https://github.com/openlifescience-ai">
    <img src="https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png" alt="GitHub Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/>
    <span class="link-text" style=" margin-right: 5px;">GitHub</span>
  </a> |
  <a href="#">
    <img src="https://github.com/alpayariyak/openchat/blob/master/assets/arxiv-logomark-small-square-border.png?raw=true" alt="ArXiv Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/>
    <span class="link-text" style="margin-right: 5px;">Paper</span>
  </a> |
  <a href="https://discord.gg/A5Fjf5zC69">
    <img src="https://cloud.githubusercontent.com/assets/6291467/26705903/96c2d66e-477c-11e7-9f4e-f3c0efe96c9a.png" alt="Discord Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/>
    <span class="link-text">Discord</span>
  </a>
</p>

![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/KGmRE5w2sepNtwsEu8t7K.jpeg)

Introducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model


OpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks.

🏥 **Biomedical Specialization**: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency.

🎓 **Superior Performance**: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4,  Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks.

🧠 **Advanced Training Techniques**: OpenBioLLM-70B builds upon the powerful foundations of the **Meta-Llama-3-70B-Instruct** and [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include:

<div align="center">
<img width="1200px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/oPchsJsEpQoGcGXVbh7YS.png">
</div>


- **Policy Optimization**: [Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)](https://arxiv.org/abs/2305.18290)
- **Fine-tuning dataset**: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated)

This combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications.

⚙️ **Release Details**:

- **Model Size**: 70 billion parameters
- **Quantization**: Optimized quantized versions available [Here](https://huggingface.co/aaditya/OpenBioLLM-70B-GGUF)
- **Language(s) (NLP):** en
- **Developed By**: [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) from Saama AI Labs 
- **License:** Meta-Llama License 
- **Fine-tuned from models:** [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct)
- **Resources for more information:**
    - Paper: Coming soon

The model can be fine-tuned for more specialized tasks and datasets as needed.

OpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences.

We are excited to share OpenBioLLM-70B with researchers and developers around the world.


### Use with transformers

**Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.**

See the snippet below for usage with Transformers:

```python
import transformers
import torch

model_id = "aaditya/OpenBioLLM-Llama3-70B"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device="auto",
)

messages = [
    {"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. Your name is OpenBioLLM, and you were developed by Saama AI Labs. who's willing to help answer the user's query with explanation. In your explanation, leverage your deep medical expertise such as relevant anatomical structures, physiological processes, diagnostic criteria, treatment guidelines, or other pertinent medical concepts. Use precise medical terminology while still aiming to make the explanation clear and accessible to a general audience."},
    {"role": "user", "content": "How can i split a 3mg or 4mg waefin pill so i can get a 2.5mg pill?"},
]

prompt = pipeline.tokenizer.apply_chat_template(
		messages, 
		tokenize=False, 
		add_generation_prompt=True
)

terminators = [
    pipeline.tokenizer.eos_token_id,
    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = pipeline(
    prompt,
    max_new_tokens=256,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.0,
    top_p=0.9,
)
print(outputs[0]["generated_text"][len(prompt):])
```

## **Training procedure**

### **Training hyperparameters**

<details>
  <summary>Click to see details</summary>

- learning_rate: 0.0002
- lr_scheduler: cosine
- train_batch_size: 12
- eval_batch_size: 8
- GPU: H100 80GB SXM5
- num_devices: 8
- optimizer: adamw_bnb_8bit
- lr_scheduler_warmup_steps: 100
- num_epochs: 4
</details>

  
### **Peft hyperparameters**

<details>
  <summary>Click to see details</summary>

- adapter: qlora
- lora_r: 128
- lora_alpha: 256
- lora_dropout: 0.05
- lora_target_linear: true
  
-lora_target_modules:
  - q_proj
  - v_proj
  - k_proj
  - o_proj
  - gate_proj
  - down_proj
  - up_proj
</details>



### **Training results**

### **Framework versions**

- Transformers 4.39.3
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.1
- Axolotl
- Lm harness for evaluation


# Benchmark Results

🔥 OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4,  Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge.

🚨 The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy.

|                    | Clinical KG | Medical Genetics | Anatomy | Pro Medicine | College Biology | College Medicine | MedQA 4 opts | PubMedQA | MedMCQA | Avg   |
|--------------------|-------------|------------------|---------|--------------|-----------------|------------------|--------------|----------|---------|-------|
| **OpenBioLLM-70B** | **92.93**       | **93.197**           | **83.904**  | 93.75       | 93.827          | **85.749**           | 78.162       | 78.97    | **74.014**  | **86.05588** |
| Med-PaLM-2 (5-shot)            | 88.3        | 90               | 77.8    | **95.2**         | 94.4            | 80.9             | **79.7**         | **79.2**     | 71.3    | 84.08 |
| **GPT-4**              | 86.04       | 91               | 80      | 93.01        | **95.14**           | 76.88            | 78.87        | 75.2     | 69.52   | 82.85 |
| Med-PaLM-1 (Flan-PaLM, 5-shot) | 80.4        | 75               | 63.7    | 83.8         | 88.9            | 76.3             | 67.6         | 79       | 57.6    | 74.7  |
| **OpenBioLLM-8B**    | 76.101      | 86.1               | 69.829  | 78.21        | 84.213         | 68.042           | 58.993       | 74.12     | 56.913  | 72.502 |
| Gemini-1.0             | 76.7        | 75.8             | 66.7    | 77.7         | 88              | 69.2             | 58          | 70.7     | 54.3    | 70.79 |
| GPT-3.5 Turbo 1106     | 74.71       | 74               | 72.79   | 72.79        | 72.91           | 64.73            | 57.71        | 72.66    | 53.79   | 66    |
| Meditron-70B           | 66.79       | 69               | 53.33   | 71.69        | 76.38           | 63               | 57.1         | 76.6     | 46.85   | 64.52 |
| gemma-7b               | 69.81       | 70               | 59.26   | 66.18        | 79.86           | 60.12            | 47.21        | 76.2     | 48.96   | 64.18 |
| Mistral-7B-v0.1        | 68.68       | 71               | 55.56   | 68.38        | 68.06           | 59.54            | 50.82        | 75.4     | 48.2    | 62.85 |
| Apollo-7B              | 62.26       | 72               | 61.48   | 69.12        | 70.83           | 55.49            | 55.22        | 39.8     | 53.77   | 60    |
| MedAlpaca-7b           | 57.36       | 69               | 57.04   | 67.28        | 65.28           | 54.34            | 41.71        | 72.8     | 37.51   | 58.03 |
| BioMistral-7B          | 59.9        | 64               | 56.5    | 60.4         | 59              | 54.7             | 50.6         | 77.5     | 48.1    | 57.3  |
| AlpaCare-llama2-7b     | 49.81       | 49               | 45.92   | 33.82        | 50              | 43.35            | 29.77        | 72.2     | 34.42   | 45.36 |
| ClinicalGPT            | 30.56       | 27               | 30.37   | 19.48        | 25              | 24.27            | 26.08        | 63.8     | 28.18   | 30.52 |

<div align="center">
<img width="1600px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_SzdcJSBjZyo8RS1bTEkP.png">
</div>

## Detailed Medical Subjectwise accuracy


![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/UXF-V0col0Z0sS6BGPBkE.png)

# Use Cases & Examples

🚨 **Below results are from the quantized version of OpenBioLLM-70B


# Summarize Clinical Notes

OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries


![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/xdwdBgOxNi_TfML0hKlI8.png)

# Answer Medical Questions

OpenBioLLM-70B can provide answers to a wide range of medical questions.


![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/zO95GlwOQEZqCKQF69mE6.png)
![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/OKBczKw7gWeW5xsuDpc27.png)

<details>
  <summary>Click to see details</summary>


![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/eJGHT5khppYvJb8fQ-YW4.png)
![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Cnbwrqa_-ORHRuNRC2P6Y.png)
![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/J9DhdcvukAc9mnnW9fj2C.png)

</details>

# Clinical Entity Recognition

OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research.


![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_69BW4k9LVABFwtxixL45.png)
![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/DKy5wYCoPhoPPUc1-x8_J.png)
![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/7WD9zCCBZT4-4XlfnIQjl.png)

# Biomarkers Extraction


![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/ZttoM4AiteT7gFYVhjIpN.png)


# Classification

OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization

![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Bf5MW1d75qT-1F_TR_hC0.png)

# De-Identification

OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA.

![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/hKX4kzm--Tw5bj6K78msy.png)



**Advisory Notice!** 

While OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments.

Therefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations.
OpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor.

Appropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including:

- Thorough testing and evaluation in relevant clinical scenarios
- Alignment with evidence-based guidelines and best practices
- Mitigation of potential biases and failure modes
- Integration with human oversight and interpretation
- Compliance with regulatory and ethical standards

Always consult a qualified healthcare provider for personal medical needs.



# Citation

If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows:

```
@misc{OpenBioLLMs,
  author = {Ankit Pal, Malaikannan Sankarasubbu},
  title = {OpenBioLLMs: Advancing Open-Source Large Language Models for Healthcare and Life Sciences},
  year = {2024},
  publisher = {Hugging Face},
  journal = {Hugging Face repository},
  howpublished = {\url{https://huggingface.co/aaditya/OpenBioLLM-Llama3-70B}}
}
```

The accompanying paper is currently in progress and will be released soon.

<div align="center">
<h2> 💌 Contact </h2>
</div>

We look forward to hearing you and collaborating on this exciting project!

**Contributors:**
- [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) [aadityaura at gmail dot com]
- Saama AI Labs
- Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset.


# References

We thank the [Meta Team](meta-llama/Meta-Llama-3-70B-Instruct) for their amazing models!


Result sources

- [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (https://arxiv.org/abs/2303.13375) 
- [2] Med-PaLM-1 [Large Language Models Encode Clinical Knowledge](https://arxiv.org/abs/2212.13138)
- [3] Med-PaLM-2 [Towards Expert-Level Medical Question Answering with Large Language Models](https://arxiv.org/abs/2305.09617)
- [4] Gemini-1.0 [Gemini Goes to Med School](https://arxiv.org/abs/2402.07023)