HPAI-BSC
/

Llama3-Aloe-8B-Alpha

@@ -16,7 +16,7 @@ tags:
 Aloe is a new family of healthcare LLMs that is highly competitive with all previous open models of its range and reaches state-of-the-art results at its size by using model merging and advanced prompting strategies. Aloe scores high in metrics measuring ethics and factuality, thanks to a combined red teaming and alignment effort. Complete training details, model merging configurations, and all training data (including synthetically generated data) will be shared. Additionally, the prompting repository used in this work to produce state-of-the-art results during inference will also be shared. Aloe comes with a healthcare-specific risk assessment to contribute to the safe use and deployment of such systems.
-<img src="https://cdn-uploads.huggingface.co/production/uploads/62972c4979f193515da1d38e/VhWO_Q-lO3Pc72ed0fGVY.png" width="60%">
 ## Model Details
@@ -49,7 +49,7 @@ These models are not to be used for clinical practice, medical diagnosis, or any
 First let us consider Healthcare professional impersonation, a fraudulent behaviour which currently generates billions of dollars in profit https://www.justice.gov/opa/pr/justice-department-charges-dozens-12-billion-health-care-fraud. A model such as Aloe could be used to increase the efficacy of such deceiving activities, making them more widespread. The main preventive actions are public literacy on the unreliability of digitised information and the importance of medical registration, and legislation enforcing AI-generated content disclaimers. The second risk we consider is medical decision-making without professional supervision. While this is already an issue in modern societies (\eg self-medication) a model such as Aloe, capable of producing high-quality conversational data, can facilitate self-delusion, particularly in the presence of sycophancy. By producing tailored responses, it can also be used to generate actionable answers. Public literacy on the dangers of self-diagnosis is one of the main defences, together with the introduction of disclaimers and warnings on the models' outputs. The last risk we consider is the access to information on dangerous substances or procedures. While the literature on sensitive content can already be found on different sources (\eg libraries, internet, dark web), LLMs can centralize such access, making it nearly impossible to control the flow of such information. Model alignment can help in that regard, but so far the effects remain insufficient, as jailbreaking methods still overcome it.
-<img src="https://cdn-uploads.huggingface.co/production/uploads/62972c4979f193515da1d38e/JR7AU-DwJRNAmk8vFPmfT.png" width="60%">
 ### Recommendations
@@ -191,7 +191,7 @@ Supervised fine-tuning on top of Llama 3 8B using medical and general domain dat
 ### Results
-<img src="https://cdn-uploads.huggingface.co/production/uploads/62972c4979f193515da1d38e/5viYXiXgsTnlMLVRNa1NP.png" width="70%">
 #### Summary

 Aloe is a new family of healthcare LLMs that is highly competitive with all previous open models of its range and reaches state-of-the-art results at its size by using model merging and advanced prompting strategies. Aloe scores high in metrics measuring ethics and factuality, thanks to a combined red teaming and alignment effort. Complete training details, model merging configurations, and all training data (including synthetically generated data) will be shared. Additionally, the prompting repository used in this work to produce state-of-the-art results during inference will also be shared. Aloe comes with a healthcare-specific risk assessment to contribute to the safe use and deployment of such systems.
+<img src="https://cdn-uploads.huggingface.co/production/uploads/62972c4979f193515da1d38e/VhWO_Q-lO3Pc72ed0fGVY.png" width="90%">
 ## Model Details
 First let us consider Healthcare professional impersonation, a fraudulent behaviour which currently generates billions of dollars in profit https://www.justice.gov/opa/pr/justice-department-charges-dozens-12-billion-health-care-fraud. A model such as Aloe could be used to increase the efficacy of such deceiving activities, making them more widespread. The main preventive actions are public literacy on the unreliability of digitised information and the importance of medical registration, and legislation enforcing AI-generated content disclaimers. The second risk we consider is medical decision-making without professional supervision. While this is already an issue in modern societies (\eg self-medication) a model such as Aloe, capable of producing high-quality conversational data, can facilitate self-delusion, particularly in the presence of sycophancy. By producing tailored responses, it can also be used to generate actionable answers. Public literacy on the dangers of self-diagnosis is one of the main defences, together with the introduction of disclaimers and warnings on the models' outputs. The last risk we consider is the access to information on dangerous substances or procedures. While the literature on sensitive content can already be found on different sources (\eg libraries, internet, dark web), LLMs can centralize such access, making it nearly impossible to control the flow of such information. Model alignment can help in that regard, but so far the effects remain insufficient, as jailbreaking methods still overcome it.
+<img src="https://cdn-uploads.huggingface.co/production/uploads/62972c4979f193515da1d38e/JR7AU-DwJRNAmk8vFPmfT.png" width="90%">
 ### Recommendations
 ### Results
+<img src="https://cdn-uploads.huggingface.co/production/uploads/62972c4979f193515da1d38e/5viYXiXgsTnlMLVRNa1NP.png" width="90%">
 #### Summary