Rx-ZJU/LLMDF

[ English | 中文 ]

Introduction

The Large Language Model for Dietary Feedback (LLMDF) is a model fine-tuned using real-world dietary feedback data from a mobile health weight management App. For details on the specific fine-tuning process, see the paper: Using Large Language Models to Generate Dietary Feedback Similar to Human Experts in Weight Management: Based on Real-world Scenario Data

Features

Advantages: The model fine-tuned using real-world data generates dietary feedback in a similar voice to local dietitians.

Disadvantages: Due to the healthcare provider interaction preferences influenced noise and effects of long-tail distribution in the real-world data, the model's response is considered lacking the ability to provide sufficient information.

Inference

LLMDF is fine-tuned from ChatGLM3-6B. When using Hugging Face's transformers for inference, it is necessary to pay attention to constructing a prompt template consistent with the dialogue format used during training.

<|user|>
Imagine you are a dietitian and you will receive dietary information from a client who is undergoing dietary management. Your task is to give the client feedback on the dietary information, and you need to provide insightful content to give the client dietary guidance to guide him towards a healthy lifestyle. \nYou can refer to organizing the dietary feedback from the following perspectives: analyzing the attributes of the food consumed by the client, providing healthy food choices, helping the client to develop a dietary pattern, encouraging the client to maintain healthy eating habits, and advising the client to modify his or her dietary habits.<MealInformation><MealType>Breakfast</MealType><MealIntakeInformation>Soy milk 1 bowl; 1 medium egg; pork, corn, and carrot glutinous rice 200 grams;</MealIntakeInformation></MealInformation><PersonalHealthInformation><Gender>Male</Gender><Age>19</Age><Height>180cm</Height><Weight>84.0kg</Weight><Waistline>85cm</Waistline><LaborIntensity>Medium</LaborIntensity></PersonalHealthInformation>
<|assistant|>

When using the prompt of the above example, the generation result of LLMDF is:

<|user|>
Imagine you are a dietitian and you will receive dietary information from a client who is undergoing dietary management. Your task is to give the client feedback on the dietary information, and you need to provide insightful content to give the client dietary guidance to guide him towards a healthy lifestyle. \nYou can refer to organizing the dietary feedback from the following perspectives: analyzing the attributes of the food consumed by the client, providing healthy food choices, helping the client to develop a dietary pattern, encouraging the client to maintain healthy eating habits, and advising the client to modify his or her dietary habits.<MealInformation><MealType>Breakfast</MealType><MealIntakeInformation>Soy milk 1 bowl; 1 medium egg; pork, corn, and carrot glutinous rice 200 grams;</MealIntakeInformation></MealInformation><PersonalHealthInformation><Gender>Male</Gender><Age>19</Age><Height>180cm</Height><Weight>84.0kg</Weight><Waistline>85cm</Waistline><LaborIntensity>Medium</LaborIntensity></PersonalHealthInformation>
<|assistant|>
<DietFeedback>Breakfast looked good! Keep it up</DietFeedback>