54 citations · 155 across the 19 of their papers we have counts for
21 papers
Position: We Need Practical AI Alignment Methods to Mirror Human Reasoning
Vijay Keswani, Breanna K. Nguyen, Cyrus Cousins +3
AI systems are increasingly employed as decision aids, decision delegates, or autonomous decision-makers. This position paper argues that in many settings, particularly high-stakes…
Moral Change or Noise? On Problems of Aligning AI With Temporally Unstable Human Feedback
Vijay Keswani, Cyrus Cousins, Breanna Nguyen +4
Alignment methods in moral domains seek to elicit moral preferences of human stakeholders and incorporate them into AI. This presupposes moral preferences as static targets, but su…
Towards Cognitively-Faithful Decision-Making Models to Improve AI Alignment
Cyrus Cousins, Vijay Keswani, Vincent Conitzer +3
Recent AI trends seek to align AI models to learned human-centric objectives, such as personal preferences, utility, or societal values. Using standard preference elicitation metho…
Can AI Model the Complexities of Human Moral Decision-Making? A Qualitative Study of Kidney Allocation Decisions
Vijay Keswani, Vincent Conitzer, Walter Sinnott-Armstrong +3
A growing body of work in Ethical AI attempts to capture human moral judgments through simple computational models. The key question we address in this work is whether such simple…
On The Stability of Moral Preferences: A Problem with Computational Elicitation Methods
Kyle Boerstler, Vijay Keswani, Lok Chan +4
Preference elicitation frameworks feature heavily in the research on participatory ethical AI tools and provide a viable mechanism to enquire and incorporate the moral values of va…
On the Pros and Cons of Active Learning for Moral Preference Elicitation
Vijay Keswani, Vincent Conitzer, Hoda Heidari +2
Computational preference elicitation methods are tools used to learn people's preferences quantitatively in a given context. Recent works on preference elicitation advocate for act…
Fair Classification with Partial Feedback: An Exploration-Based Data Collection Approach
Vijay Keswani, Anay Mehrotra, L. Elisa Celis
In many predictive contexts (e.g., credit lending), true outcomes are only observed for samples that were positively classified in the past. These past observations, in turn, form…
Designing Closed-Loop Models for Task Allocation
Vijay Keswani, L. Elisa Celis, Krishnaram Kenthapadi +1
Automatically assigning tasks to people is challenging because human performance can vary across tasks for many reasons. This challenge is further compounded in real-life settings…
Diverse Representation via Computational Participatory Elections -- Lessons from a Case Study
Florian Evéquoz, Johan Rochel, Vijay Keswani +1
Elections are the central institution of democratic processes, and often the elected body -- in either public or private governance -- is a committee of individuals. To ensure the…
Addressing Strategic Manipulation Disparities in Fair Classification
Vijay Keswani, L. Elisa Celis
In real-world classification settings, such as loan application evaluation or content moderation on online platforms, individuals respond to classifier predictions by strategically…
Designing Closed Human-in-the-loop Deferral Pipelines
Vijay Keswani, Matthew Lease, Krishnaram Kenthapadi
In hybrid human-machine deferral frameworks, a classifier can defer uncertain cases to human decision-makers (who are often themselves fallible). Prior work on simultaneous trainin…
Auditing for Diversity using Representative Examples
Vijay Keswani, L. Elisa Celis
Assessing the diversity of a dataset of information associated with people is crucial before using such data for downstream applications. For a given dataset, this often involves c…
Towards Unbiased and Accurate Deferral to Multiple Experts
Vijay Keswani, Matthew Lease, Krishnaram Kenthapadi
Machine learning models are often implemented in cohort with humans in the pipeline, with the model having an option to defer to a domain expert in cases where it has low confidenc…
Dialect Diversity in Text Summarization on Twitter
Vijay Keswani, L. Elisa Celis
Discussions on Twitter involve participation from different communities with different dialects and it is often necessary to summarize a large number of posts into a representative…
A Convergent and Dimension-Independent Min-Max Optimization Algorithm
Vijay Keswani, Oren Mangoubi, Sushant Sachdeva +1
We study a variant of a recently introduced min-max optimization framework where the max-player is constrained to update its parameters in a greedy manner until it reaches a first-…
Data preprocessing to mitigate bias: A maximum entropy based approach
L. Elisa Celis, Vijay Keswani, Nisheeth K. Vishnoi
Data containing human or social attributes may over- or under-represent groups with respect to salient social attributes such as gender or race, which can lead to biases in downstr…
Improved Adversarial Learning for Fair Classification
L. Elisa Celis, Vijay Keswani
Motivated by concerns that machine learning algorithms may introduce significant bias in classification models, developing fair classifiers has become an important problem in machi…
Implicit Diversity in Image Summarization
L. Elisa Celis, Vijay Keswani
Studies have shown that the people depicted in image search results tend to be of majority groups with respect to socially salient attributes. This skew goes beyond that which alre…
Balanced News Using Constrained Bandit-based Personalization
Sayash Kapoor, Vijay Keswani, Nisheeth K. Vishnoi +1
We present a prototype for a news search engine that presents balanced viewpoints across liberal and conservative articles with the goal of de-polarizing content and allowing users…
Classification with Fairness Constraints: A Meta-Algorithm with Provable Guarantees
L. Elisa Celis, Lingxiao Huang, Vijay Keswani +1
Developing classification algorithms that are fair with respect to sensitive attributes of the data has become an important problem due to the growing deployment of classification…
Fair and Diverse DPP-based Data Summarization
L. Elisa Celis, Vijay Keswani, Damian Straszak +3
Sampling methods that choose a subset of the data proportional to its diversity in the feature space are popular for data summarization. However, recent studies have noted the occu…