466 citations · 568 across the 13 of their papers we have counts for
14 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…
A Simple, Statistically Robust Test of Discrimination
Johann D. Gaebler, Sharad Goel
In observational studies of discrimination, the most common statistical approaches consider either the rate at which decisions are made (benchmark tests) or the success rate of tho…
Auditing the Use of Language Models to Guide Hiring Decisions
Johann D. Gaebler, Sharad Goel, Aziz Huq +1
Regulatory efforts to protect against algorithmic bias have taken on increased urgency with rapid advances in large language models (LLMs), which are machine learning models that c…
Causal Conceptions of Fairness and their Consequences
Hamed Nilforoshan, Johann Gaebler, Ravi Shroff +1
Recent work highlights the role of causality in designing equitable decision-making algorithms. It is not immediately clear, however, how existing causal conceptions of fairness re…
An Adaptive State Aggregation Algorithm for Markov Decision Processes
Guanting Chen, Johann Demetrio Gaebler, Matt Peng +2
Value iteration is a well-known method of solving Markov Decision Processes (MDPs) that is simple to implement and boasts strong theoretical convergence guarantees. However, the co…
Blocks as geographic discontinuities: The effect of polling place assignment on voting
Sabina Tomkins, Keniel Yao, Johann Gaebler +4
A potential voter must incur a number of costs in order to successfully cast an in-person ballot, including the costs associated with identifying and traveling to a polling place.…
A Causal Framework for Observational Studies of Discrimination
Johann Gaebler, William Cai, Guillaume Basse +3
In studies of discrimination, researchers often seek to estimate a causal effect of race or gender on outcomes. For example, in the criminal justice context, one might ask whether…
Fair Allocation through Selective Information Acquisition
William Cai, Johann Gaebler, Nikhil Garg +1
Public and private institutions must often allocate scare resources under uncertainty. Banks, for example, extend credit to loan applicants based in part on their estimated likelih…
Mitigating Included- and Omitted-Variable Bias in Estimates of Disparate Impact
Jongbin Jung, Sam Corbett-Davies, Johann D. Gaebler +2
Managers, employers, policymakers, and others often seek to understand whether decisions are biased against certain groups. One popular analytic strategy is to estimate disparities…
The Measure and Mismeasure of Fairness
Sam Corbett-Davies, Johann D. Gaebler, Hamed Nilforoshan +2
The field of fair machine learning aims to ensure that decisions guided by algorithms are equitable. Over the last decade, several formal, mathematical definitions of fairness have…
Partially Bounded Transformations have Trivial Centralizer
Johann Gaebler, Alexander Kastner, Cesar E. Silva +2
We prove that for infinite rank-one transformations satisfying a property called "partial boundedness," the only commuting transformations are powers of the original transformation…