Learn Hands-on Skills to Minimize Hallucinations in AI-Generated Content
Given the rapid integration of AI writing tools into our academic and research environments, the need to ensure the accuracy and reliability of AI-generated content has never been more pressing. We invite faculty and students from WashU to join us in a comprehensive workshop designed to address and reduce hallucinations in large language models.
Why Attend?
- Addressing Key Pain Points: Are you concerned about non-existent citations, non-factual mistakes, or errors in interpretation? This workshop targets these issues head-on, providing you with the skills to identify and correct these errors in AI-generated content.
- Objective Insights: Receive a balanced overview of proven strategies to minimize hallucinations in AI outputs. Our focus is on delivering practical, evidence-based methods that enhance the trustworthiness of AI-generated content.
- Concise and Impactful Learning: Through concise case studies and examples, gain hands-on experience in prompt engineering, custom tooling, fact-checking, and database grounding. Learn to navigate and correct common AI-generated errors efficiently.
This workshop is crafted to meet the needs of both faculty and students, providing essential skills for anyone looking to improve the reliability of AI-generated content. Whether you’re seeking to understand the nuances of AI-generated errors or looking for effective ways to ensure the accuracy of your AI tools, this workshop will offer valuable insights and practical solutions.
Professor Ruopeng An conducts research to assess population-level policies, local food and built environment, and socioeconomic determinants that affect individuals’ dietary behavior, physical activity, sedentary lifestyle, and adiposity in children, adults of all ages, and people with disabilities. His research aims to develop a well-rounded knowledge base and policy recommendations that can inform decision-making and the allocation of resources to combat obesity.
An’s research has been funded by federal agencies and public/private organizations (e.g., OpenAI, Abbott, Amgen). He has wide teaching and methodological expertise, including applied artificial intelligence (machine and deep learning), quantitative policy analysis (causal inference, cost-benefit and cost-effectiveness analysis, and microsimulation), applied econometrics and regression analysis, and systematic review and meta-analysis. He founded and chairs the Artificial Intelligence and Big Data Analytics for Public Health (AIBDA) Certificate program and hosts the “Artificial Intelligence in the Social Sciences” Open Classroom series. He has repeatedly been recognized for teaching excellence, receiving student evaluations in the top 10% of University faculty.
Register to Attend