5 papers
Evaluating Large Language Models for Antisemitic Incident Classification
Karina Halevy, Julia Mendelsohn, Chan Young Park +2
Addressing hate and violence in society requires timely detection of hateful events from public reporting, but automated identification of hateful events remains underexplored. We…
Who's the (Multi-)Fairest of Them All: Rethinking Interpolation-Based Data Augmentation Through the Lens of Multicalibration
Karina Halevy, Karly Hou, Charumathi Badrinath
Data augmentation methods, especially SoTA interpolation-based methods such as Fair Mixup, have been widely shown to increase model fairness. However, this fairness is evaluated on…
"Flex Tape Can't Fix That": Bias and Misinformation in Edited Language Models
Karina Halevy, Anna Sotnikova, Badr AlKhamissi +2
Model editing has emerged as a cost-effective strategy to update knowledge stored in language models. However, model editing can have unintended consequences after edits are applie…
A Group-Specific Approach to NLP for Hate Speech Detection
Karina Halevy
Automatic hate speech detection is an important yet complex task, requiring knowledge of common sense, stereotypes of protected groups, and histories of discrimination, each of whi…
Evaluating Word Embeddings with Categorical Modularity
Sílvia Casacuberta, Karina Halevy, Damián E. Blasi
We introduce categorical modularity, a novel low-resource intrinsic metric to evaluate word embedding quality. Categorical modularity is a graph modularity metric based on the -…