Related papers: Audits as Evidence: Experiments, Ensembles, and En…
The deployment of Large Language Models (LLMs) as tool-using agents causes their alignment training to manifest in new ways. Recent work finds that language models can use tools in ways that contradict the interests or explicit instructions…
We study a dynamic labor market in which a risk-averse worker with career concerns chooses each period between self-employment, which generates publicly observed binary output, and employment at a firm, which pays a flat wage but keeps…
Ad platforms such as Facebook, Google and LinkedIn promise value for advertisers through their targeted advertising. However, multiple studies have shown that ad delivery on such platforms can be skewed by gender or race due to hidden…
Discriminatory job vacancies are disapproved worldwide, but remain persistent. Discrimination in job vacancies can be explicit by directly referring to demographic memberships of candidates. More implicit forms of discrimination are also…
I study labor markets in which firms hire via referrals. I develop an employment model showing that--despite initial equality in ability, employment, wages, and network structure--minorities receive fewer jobs through referral and lower…
Algorithmic discrimination is a condition that arises when data-driven software unfairly treats users based on attributes like ethnicity, race, gender, sexual orientation, religion, age, disability, or other personal characteristics.…
Individuals with similar qualifications and skills may vary in their demeanor, or outward manner: some tend toward self-promotion while others are modest to the point of omitting crucial information. Comparing the self-descriptions of…
In the criminal legal context, risk assessment algorithms are touted as data-driven, well-tested tools. Studies known as validation tests are typically cited by practitioners to show that a particular risk assessment algorithm has…
Large language models (LLMs) have shown remarkable adaptability to diverse tasks, by leveraging context prompts containing instructions, or minimal input-output examples. However, recent work revealed they also exhibit label bias -- an…
Digital discrimination is a form of discrimination whereby users are automatically treated unfairly, unethically or just differently based on their personal data by a machine learning (ML) system. Examples of digital discrimination include…
In order to estimate causal effects in a randomized experiment where spillovers are suspected to occur, analysts must posit a model of interference. The most popular class of interference models are those based on exposure mappings. In…
We systematically investigate the effect heterogeneity of job search programmes for unemployed workers. To investigate possibly heterogeneous employment effects, we combine non-experimental causal empirical models with Lasso-type…
Scalable oversight studies methods of training and evaluating AI systems in domains where human judgment is unreliable or expensive, such as scientific research and software engineering in complex codebases. Most work in this area has…
We study hypothesis testing over a heterogeneous population of strategic agents with private information. Any single test applied uniformly across the population yields statistical error that is sub-optimal relative to the performance of an…
In traditional decision making processes, social biases of human decision makers can lead to unequal economic outcomes for underrepresented social groups, such as women, racial or ethnic minorities. Recently, the increasing popularity of…
All methodologies for detecting plagiarism to date have focused on the final digital "outcome", such as a document or source code. Our novel approach takes the creation process into account using logged events collected by special software…
Attrition is a common and potentially important threat to internal validity in treatment effect studies. We extend the changes-in-changes approach to identify the average treatment effect for respondents and the entire study population in…
We study the production, entry, and technological decisions of firms in the presence of bribery. We find that bribery can be justified even in the absence of bureaucratic inefficiencies. We document substantial technology-specific…
An employer contracts with a worker to incentivize efforts whose productivity depends on ability; the worker then enters a market that pays him contingent on ability evaluation. With non-additive monitoring technology, the interdependence…
Alternative data provides valuable insights for lenders to evaluate a borrower's creditworthiness, which could help expand credit access to underserved groups and lower costs for borrowers. But some forms of alternative data have…