We are excited to share that Haley Triem, one of our talented NRT students, has been awarded the Second Top Poster at the NSF NRT Annual Meeting. Her research presentation, “Tipping the Balance: Human Intervention in Large Language Model Multiagent Debate,” was recognized for its innovative exploration of the role of human intervention in AI debates.
Haley’s poster highlights how Large Language Models (LLMs) can be guided through mechanism engineering, addressing both technical and ethical concerns in AI reasoning. Her work delves into experiments involving synthetic, multiagent, and human-AI debates, revealing valuable insights on how LLMs interact and respond to human input.
We are proud of Haley’s outstanding achievement and her representation of our Ethical AI research team. Below is a look at her award-winning poster:
