Meng Chen
HCI + AI Researcher
I work on Human-AI Interaction. I am interested in making the communication between humans and LLM-powered systems more effective and reliable.
  • Execution Humans and LLMs now collaborate on open-ended complex tasks. How can we make interactions communicative to complement their strengths?
  • Evaluation LLM outputs (e.g., reports, series of actions) are long and hard to evaluate. How can users oversight during the process when misalignments and threats are subtle?

I am a 2nd-year CS PhD student at UC Berkeley advised by Amy Pavel. I obtained my Bachelor's degree in Computer Science and Philosophy from the University of Notre Dame where I worked closely with Toby Jia-jun Li.
Featured Projects
Surfacing Variations to Calibrate Perceived Reliability of MLLM-Generated Image Descriptions

Surfacing Variations to Calibrate Perceived Reliability of MLLM-Generated Image Descriptions

Meng Chen, Akhil Iyer, Amy Pavel

ASSETS 2025

Project Page Paper
Luminate: Structured Generation and Exploration of Design Space with Large Language Models for Human-AI Co-Creation

Luminate: Structured Generation and Exploration of Design Space with Large Language Models for Human-AI Co-Creation

Sangho Suh*, Meng Chen*, Bryan Min, Toby Jia-Jun Li, Haijun Xia

CHI 2024

Project Page Video Paper
News