Publications (43)
Equilibria, Efficiency, and Inequality in Network Formation for Hiring and Opportunity
Cynthia Dwork, Chris Hays, Jon Kleinberg +1
Professional networks -- the social networks among people in a given line of work -- can serve as a conduit for job prospects and other opportunities. Here we propose a model for t…
Homogeneous Algorithms Can Reduce Competition in Personalized Pricing
Nathanael Jo, Kathleen Creel, Ashia Wilson +1
Firms' algorithm development practices are often homogeneous. Whether firms train algorithms on similar data, aim at similar benchmarks, or rely on similar pre-trained models, the…
Greedy Algorithm almost Dominates in Smoothed Contextual Bandits
Manish Raghavan, Aleksandrs Slivkins, Jennifer Wortman Vaughan +1
Online learning algorithms, widely used to power search and content optimization on the web, must balance exploration and exploitation, potentially sacrificing the experience of cu…
Content Moderation and the Formation of Online Communities: A Theoretical Framework
Cynthia Dwork, Chris Hays, Jon Kleinberg +1
We study the impact of content moderation policies in online communities. In our theoretical model, a platform chooses a content moderation policy and individuals choose whether or…
Algorithmic Monoculture and its Critics
Brian Hedden, Manish Raghavan
Algorithmic decision-making is replacing idiosyncratic human judgment in domains such as hiring, lending, and criminal justice. This shift promises increased consistency, but many…
Auditing for Human Expertise
Rohan Alur, Loren Laine, Darrick K. Li +3
High-stakes prediction tasks (e.g., patient diagnosis) are often handled by trained human experts. A common source of concern about automation in these settings is that experts may…
Reconciling the accuracy-diversity trade-off in recommendations
Kenny Peng, Manish Raghavan, Emma Pierson +2
In recommendation settings, there is an apparent trade-off between the goals of accuracy (to recommend items a user is most likely to want) and diversity (to recommend items repres…
Strategic Candidacy in Generative AI Arenas
Chris Hays, Rachel Li, Bailey Flanigan +1
AI arenas, which rank generative models from pairwise preferences of users, are a popular method for measuring the relative performance of models in the course of their organic use…
How Do Classifiers Induce Agents To Invest Effort Strategically?
Jon Kleinberg, Manish Raghavan
Algorithms are often used to produce decision-making rules that classify or evaluate individuals. When these individuals have incentives to be classified a certain way, they may be…
Planning Problems for Sophisticated Agents with Present Bias
Jon Kleinberg, Sigal Oren, Manish Raghavan
Present bias, the tendency to weigh costs and benefits incurred in the present too heavily, is one of the most widespread human behavioral biases. It has also been the subject of e…
Roles for Computing in Social Change
Rediet Abebe, Solon Barocas, Jon Kleinberg +3
A recent normative turn in computer science has brought concerns about fairness, bias, and accountability to the core of the field. Yet recent scholarship has warned that much of t…
The Hidden Assumptions Behind Counterfactual Explanations and Principal Reasons
Solon Barocas, Andrew D. Selbst, Manish Raghavan
Counterfactual explanations are gaining prominence within technical, legal, and business circles as a way to explain the decisions of a machine learning model. These explanations s…
Synthetic Census Data Generation via Multidimensional Multiset Sum
Cynthia Dwork, Kristjan Greenewald, Manish Raghavan
The US Decennial Census provides valuable data for both research and policy purposes. Census data are subject to a variety of disclosure avoidance techniques prior to release in or…
Simplistic Collection and Labeling Practices Limit the Utility of Benchmark Datasets for Twitter Bot Detection
Chris Hays, Zachary Schutzman, Manish Raghavan +2
Accurate bot detection is necessary for the safety and integrity of online platforms. It is also crucial for research on the influence of bots in elections, the spread of misinform…
Impacts of Aggregation on Model Diversity and Consumer Utility
Kate Donahue, Manish Raghavan
Consider a marketplace of AI tools, each with slightly different strengths and weaknesses. By picking the right model for the task at hand, a user can do better than simply using t…
Algorithmic Monoculture and Social Welfare
Jon Kleinberg, Manish Raghavan
As algorithms are increasingly applied to screen applicants for high-stakes decisions in employment, lending, and other domains, concerns have been raised about the effects of algo…
Integrating Expert Judgment and Algorithmic Decision Making: An Indistinguishability Framework
Rohan Alur, Loren Laine, Darrick K. Li +3
We introduce a novel framework for human-AI collaboration in prediction and decision tasks. Our approach leverages human judgment to distinguish inputs which are algorithmically in…
Stochastic Model for Sunk Cost Bias
Jon Kleinberg, Sigal Oren, Manish Raghavan +1
We present a novel model for capturing the behavior of an agent exhibiting sunk-cost bias in a stochastic environment. Agents exhibiting sunk-cost bias take into account the effort…
Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practices
Manish Raghavan, Solon Barocas, Jon Kleinberg +1
There has been rapidly growing interest in the use of algorithms in hiring, especially as a means to address or mitigate bias. Yet, to date, little is known about how these methods…
Planning with Multiple Biases
Jon Kleinberg, Sigal Oren, Manish Raghavan
Recent work has considered theoretical models for the behavior of agents with specific behavioral biases: rather than making decisions that optimize a given payoff function, the ag…
Inherent Trade-Offs in the Fair Determination of Risk Scores
Jon Kleinberg, Sendhil Mullainathan, Manish Raghavan
Recent discussion in the public sphere about algorithmic classification has involved tension between competing notions of what it means for a probabilistic classification to be fai…
Statistical Guarantees in the Search for Less Discriminatory Algorithms
Chris Hays, Ben Laufer, Solon Barocas +1
U.S. discrimination law can impose liability on firms that fail to adopt a less discriminatory alternative (LDA): a decision policy that achieves the same business objectives while…
Evaluating the Impacts of Swapping on the US Decennial Census
Maria Ballesteros, Cynthia Dwork, Gary King +2
To meet its dual burdens of providing useful statistics and ensuring privacy of individual respondents, the US Census Bureau has for decades introduced some form of "noise" into pu…
What Constitutes a Less Discriminatory Algorithm?
Benjamin Laufer, Manish Raghavan, Solon Barocas
Disparate impact doctrine offers an important legal apparatus for targeting discriminatory data-driven algorithmic decisions. A recent body of work has focused on conceptualizing o…
Fairness On The Ground: Applying Algorithmic Fairness Approaches to Production Systems
Chloé Bakalar, Renata Barreto, Stevie Bergman +13
Many technical approaches have been proposed for ensuring that decisions made by machine learning systems are fair, but few of these proposals have been stress-tested in real-world…
Bridging Machine Learning and Mechanism Design towards Algorithmic Fairness
Jessie Finocchiaro, Roland Maio, Faidra Monachou +4
Decision-making systems increasingly orchestrate our world: how to intervene on the algorithmic components to build fair and equitable systems is therefore a question of utmost imp…
Unstable Unlearning: The Hidden Risk of Concept Resurgence in Diffusion Models
Vinith M. Suriyakumar, Rohan Alur, Ayush Sekhari +2
Text-to-image diffusion models rely on massive, web-scale datasets. Training them from scratch is computationally expensive, and as a result, developers often prefer to make increm…
Mapping the Invocation Structure of Online Political Interaction
Manish Raghavan, Ashton Anderson, Jon Kleinberg
The surge in political information, discourse, and interaction has been one of the most important developments in social media over the past several years. There is rich structure…
On Fairness and Calibration
Geoff Pleiss, Manish Raghavan, Felix Wu +2
The machine learning community has become increasingly concerned with the potential for bias and discrimination in predictive models. This has motivated a growing line of work on w…
Competition and Diversity in Generative AI
Manish Raghavan
Recent evidence, both in the lab and in the wild, suggests that the use of generative artificial intelligence reduces the diversity of content produced. The use of the same or simi…
Incentives shape how humans co-create with generative AI
Nathanael Jo, Manish Raghavan
Generative AI is quickly becoming an integral part of people's everyday workflows. Early evidence has shown that while generative AI can increase individual-level productivity, it…
The Right to be an Exception to a Data-Driven Rule
Sarah H. Cen, Manish Raghavan
Data-driven tools are increasingly used to make consequential decisions. They have begun to advise employers on which job applicants to interview, judges on which defendants to gra…
The Subjectivity of Monoculture
Nathanael Jo, Nikhil Garg, Manish Raghavan
Machine learning models -- including large language models (LLMs) -- are often said to exhibit monoculture, where outputs agree strikingly often. But what does it actually mean for…
The Impossibility of Inverse Permutation Learning in Transformer Models
Rohan Alur, Chris Hays, Manish Raghavan +1
In this technical note, we study the problem of inverse permutation learning in decoder-only transformers. Given a permutation and a string to which that permutation has been appli…
Human Expertise in Algorithmic Prediction
Rohan Alur, Manish Raghavan, Devavrat Shah
We introduce a novel framework for incorporating human expertise into algorithmic predictions. Our approach leverages human judgment to distinguish inputs which are algorithmically…
Evaluating multiple models using labeled and unlabeled data
Divya Shanmugam, Shuvom Sadhuka, Manish Raghavan +3
It remains difficult to evaluate machine learning classifiers in the absence of a large, labeled dataset. While labeled data can be prohibitively expensive or impossible to obtain,…
Double Machine Learning for Causal Inference under Shared-State Interference
Chris Hays, Manish Raghavan
Researchers and practitioners often wish to measure treatment effects in settings where units interact via markets and recommendation systems. In these settings, units are affected…
When to Ask a Question: Understanding Communication Strategies in Generative AI Tools
Charlotte Park, Kate Donahue, Manish Raghavan
Generative AI models differ from traditional machine learning tools in that they allow users to provide as much or as little information as they choose in their inputs. This flexib…
The Externalities of Exploration and How Data Diversity Helps Exploitation
Manish Raghavan, Aleksandrs Slivkins, Jennifer Wortman Vaughan +1
Online learning algorithms, widely used to power search and content optimization on the web, must balance exploration and exploitation, potentially sacrificing the experience of cu…
Selection Problems in the Presence of Implicit Bias
Jon Kleinberg, Manish Raghavan
Over the past two decades, the notion of implicit bias has come to serve as an important component in our understanding of discrimination in activities such as hiring, promotion, a…
Hiring Under Uncertainty
Manish Raghavan, Manish Purohit, Sreenivas Gollupadi
In this paper we introduce the hiring under uncertainty problem to model the questions faced by hiring committees in large enterprises and universities alike. Given a set of el…
Hitting a Moving Target: Test-Time Adaptation for AI Text Detection under Continual Distribution Shift
Kevin Ren, Manish Raghavan, Nikhil Garg
Deployed approaches for AI text detection often rely on training-time access to labeled datasets of both human-written and AI-generated text. This approach is vulnerable to three t…
The Challenge of Understanding What Users Want: Inconsistent Preferences and Engagement Optimization
Jon Kleinberg, Sendhil Mullainathan, Manish Raghavan
Online platforms have a wealth of data, run countless experiments and use industrial-scale algorithms to optimize user experience. Despite this, many users seem to regret the time…