Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values?
arXiv, 2025
Humans often act in ways that are inconsistent with their values. We hypothesize that this is also true for LLMs.
Publications
You can also find my articles on my Google Scholar profile.
Preprints
LLM Confidence Evaluation Measures in Zero-Shot CSS Classification
arXiv, 2024
A novel uncertainty quantification method for LLMs.
Publications
LLMs Among Us: Generative AI Participating in Digital Discourse
AAAI Spring Symposium, 2024
Do social media users realize that they are interacting with bots? Short answer: probably not.
Defending novice user privacy: An evaluation of default web browser configurations
Computers & Security, 2024
Which web browser has the best default privacy settings?
Posters
Epistemic Positioning in Large Language Models
RAISE Winter Exposition, 2025
Translating classical problems in epistemology to the setting of large language models.
