Can LLMs Simulate Personas with Reversed Performance? A Benchmark for Counterfactual Instruction Following

Large Language Models (LLMs) are now increasingly widely used to simulate personas in virtual environments, leveraging their instruction-following capability. However, we discovered that even state-of-the-art LLMs cannot simulate personas with reversed performance (e.g., student personas with low proficiency in educational settings), which impairs the simulation diversity and limits the practical applications of the simulated environments. In this work, using mathematical reasoning as a representative scenario, we propose the first benchmark dataset for evaluating LLMs on simulating personas with reversed performance, a capability that we dub “counterfactual instruction following”. We evaluate both open-weight and closed-source LLMs on this task and find that LLMs, including the OpenAI o1 reasoning model, all struggle to follow counterfactual instructions for simulating reversedly performing personas. Intersectionally simulating both the performance level and the race population of a persona worsens the effect even further. These results highlight the challenges of counterfactual instruction following and the need for further research.

Ryan Watkins

Professor at George Washington University

I am a Professor with Human-Technology Collaboration and Educational Technology programs at George Washington University in Washington DC. I have written 12 books and more than 100 articles, and I co-host of the Parsing Science podcast where scientists tell the stories behind their research. I am also the developer of the WeShareScience.com online platform for sharing research videos, and SciencePods.com where researchers can create free podcasts about their science. My research interests include human interactions with intelligent machines, needs, needs assessments, and instructional design.