7.4k citations · 22.9k across the 86 of their papers we have counts for
7 papers · 1 filter
Quantile Risk Control: A Flexible Framework for Bounding the Probability of High-Loss Predictions
Jake C. Snell, Thomas P. Zollo, Zhun Deng +2
Rigorous guarantees about the performance of predictive algorithms are necessary in order to ensure their responsible use. Previous work has largely focused on bounding the expecte…
Is the Elephant Flying? Resolving Ambiguities in Text-to-Image Generative Models
Ninareh Mehrabi, Palash Goyal, Apurv Verma +7
Natural language often contains ambiguities that can lead to misinterpretation and miscommunication. While humans can handle ambiguities effectively by asking clarifying questions…
Semantically Informed Slang Interpretation
Zhewei Sun, Richard Zemel, Yang Xu
Slang is a predominant form of informal language making flexible and extended use of words that is notoriously hard for natural language processing systems to interpret. Existing a…
Differentially Private Decoding in Large Language Models
Jimit Majmudar, Christophe Dupuy, Charith Peris +3
Recent large-scale natural language processing (NLP) systems use a pre-trained Large Language Model (LLM) on massive and diverse corpora as a headstart. In practice, the pre-traine…
Mapping the Multilingual Margins: Intersectional Biases of Sentiment Analysis Systems in English, Spanish, and Arabic
António Câmara, Nina Taneja, Tamjeed Azad +2
As natural language processing systems become more widespread, it is necessary to address fairness issues in their implementation and deployment to ensure that their negative impac…
Deep Ensembles Work, But Are They Necessary?
Taiga Abe, E. Kelly Buchanan, Geoff Pleiss +2
Ensembling neural networks is an effective way to increase accuracy, and can often match the performance of individual larger models. This observation poses a natural question: giv…