9 papers
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…
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 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…
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,…