Creating a Humanitarian LLM Chatbot Website for Crisis Support
"Team #35's Universal Response Engine project aims to develop a chatbot-like platform providing tailored support for mental health, medical assistance, legal guidance, housing advice, and disaster information. By utilizing multimodal responses, the system addresses the inefficiencies and stress faced by those in need. The solution prioritizes user-centered design, ethical AI practices, and data security while adhering to engineering standards and ethical guidelines."
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
Team #35 Universal Response Engine: LLMs for Good Client: Ahmed Nazar Advisor: Mohamed Selim
Project Overview Creating an LLM for humanitarian use Chatbot-like website where users provide questions/prompts Model responds with relevant links, media, info (multimodal)
Problem Statement The lack of a comprehensive platform to provide support to the aforementioned people in need causes: 1. Increased stress and frustration 2. Inefficient use of time and energy 3. Potential oversight of crucial information/services 4. Inconsistent quality and reliability of info
User Needs Mental health questions Medical assistance Legal direction Housing advice Disaster information
Requirements User Experience Accessible design Easy to understand layout Users can input text and image queries Knowledgeable, concise, and fast responses Should create a sense of care and support Technical Access to internet and a web browser Hosted on ISU servers Ethical Application does not store users private information The LLM is vetted for appropriate responses Datasets used contain appropriate and relevant information
Engineering Standards ISO/IEC 27000: Information security management ISO/IEC 42001: Artificial Intelligence Management System IEEE Std 730-2014: Standard for Software Quality Assurance Processes IEEE Std 1028-2008: Standard for Software Reviews and Audits IEEE/ISO/IEC 26514-2021: Design and development of information for users
Conclusions 1. Our platform will provide users with concise answers to their queries and/or guide them to relevant resources. 2. We will prioritize user-centric design and ethical AI practices, while maintaining user privacy and data security. 3. This solution streamlines the help-seeking process while adhering to engineering standards and ethical guidelines.
