11 citations · 24 across the 12 of their papers we have counts for
12 papers
What's In My Human Feedback? Learning Interpretable Descriptions of Preference Data
Rajiv Movva, Smitha Milli, Sewon Min +1
Human feedback can alter language models in unpredictable and undesirable ways, as practitioners lack a clear understanding of what feedback data encodes. While prior work studies…
Position: Use Sparse Autoencoders to Discover Unknowns
Kenny Peng, Rajiv Movva, Jon Kleinberg +2
While sparse autoencoders (SAEs) have generated significant excitement, a series of negative results have added to skepticism about their usefulness. Here, we establish a conceptua…
Sparse Autoencoders for Hypothesis Generation
Rajiv Movva, Kenny Peng, Nikhil Garg +2
We describe HypotheSAEs, a general method to hypothesize interpretable relationships between text data (e.g., headlines) and a target variable (e.g., clicks). HypotheSAEs has three…
Generative AI in Medicine
Divya Shanmugam, Monica Agrawal, Rajiv Movva +4
The increased capabilities of generative AI have dramatically expanded its possible use cases in medicine. We provide a comprehensive overview of generative AI use cases for clinic…
Annotation alignment: Comparing LLM and human annotations of conversational safety
Rajiv Movva, Pang Wei Koh, Emma Pierson
Do LLMs align with human perceptions of safety? We study this question via annotation alignment, the extent to which LLMs and humans agree when annotating the safety of user-chatbo…
Using large language models to promote health equity
Emma Pierson, Divya Shanmugam, Rajiv Movva +12
Advances in large language models (LLMs) have driven an explosion of interest about their societal impacts. Much of the discourse around how they will impact social equity has been…
Topics, Authors, and Institutions in Large Language Model Research: Trends from 17K arXiv Papers
Rajiv Movva, Sidhika Balachandar, Kenny Peng +3
Large language models (LLMs) are dramatically influencing AI research, spurring discussions on what has changed so far and how to shape the field's future. To clarify such question…
Coarse race data conceals disparities in clinical risk score performance
Rajiv Movva, Divya Shanmugam, Kaihua Hou +4
Healthcare data in the United States often records only a patient's coarse race group: for example, both Indian and Chinese patients are typically coded as "Asian." It is unknown,…
Combining Compressions for Multiplicative Size Scaling on Natural Language Tasks
Rajiv Movva, Jinhao Lei, Shayne Longpre +2
Quantization, knowledge distillation, and magnitude pruning are among the most popular methods for neural network compression in NLP. Independently, these methods reduce model size…
Fairness Deconstructed: A Sociotechnical View of 'Fair' Algorithms in Criminal Justice
Rajiv Movva
Early studies of risk assessment algorithms used in criminal justice revealed widespread racial biases. In response, machine learning researchers have developed methods for fairnes…
Studying the Consistency and Composability of Lottery Ticket Pruning Masks
Rajiv Movva, Jonathan Frankle, Michael Carbin
Magnitude pruning is a common, effective technique to identify sparse subnetworks at little cost to accuracy. In this work, we ask whether a particular architecture's accuracy-spar…
Dissecting Lottery Ticket Transformers: Structural and Behavioral Study of Sparse Neural Machine Translation
Rajiv Movva, Jason Y. Zhao
Recent work on the lottery ticket hypothesis has produced highly sparse Transformers for NMT while maintaining BLEU. However, it is unclear how such pruning techniques affect a mod…