5 papers
From Constitutions to Control: Interpretable Rewards for Aligning Language Models
Johann D. Gaebler, Calvin Isley, Max Lamparth +2
Current approaches to aligning language models often make it hard to know what behavior is being rewarded or to change that reward in a targeted way. In particular, standard prefer…
Receptiveness, Not Sycophancy: Distinguishing Engagement from Deference in Language Models
Calvin Isley, Johann Gaebler, Max Lamparth +2
A central concern with language models is sycophancy: their tendency to defer to users' views at the expense of independent substantive judgment. In parallel, work on social sycoph…
AI-written admissions essays are widespread but penalized
Calvin Isley, Johann D. Gaebler, Sharad Goel
AI is rapidly transforming higher education, including the application process, yet relatively little is known about its use and consequences. To help close this gap, we analyze ne…
Mitigating Label Bias with Interpretable Rubric Embeddings
Calvin Isley, Johann D. Gaebler, Sharad Goel
Statistical decision algorithms are increasingly deployed in domains where ground-truth labels are hard to obtain, such as hiring, university admissions, and content moderation. In…
Assessing the Quality of AI-Generated Exams: A Large-Scale Field Study
Calvin Isley, Joshua Gilbert, Evangelos Kassos +9
While large language models (LLMs) challenge conventional methods of teaching and learning, they present an exciting opportunity to improve efficiency and scale high-quality instru…