Papers by Karina Halevy
“Flex Tape Can’t Fix That”: Bias and Misinformation in Edited Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Weight-based model editing methods can unintentionally alter unrelated parametric knowledge representations, potentially increasing the risk of harm. |
| Approach: | They propose a benchmark dataset for measuring bias amplification of model editing methods for demographic traits such as race, geographic origin, and gender. |
| Outcome: | The proposed methods can unintentionally alter unrelated parametric knowledge representations, potentially increasing the risk of harm. |
Evaluating Word Embeddings with Categorical Modularity (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing word embeddings use different bilingual supervision signals with varying levels of strength. |
| Approach: | They propose a graph modularity metric to measure word embedding quality . they use a set of 500 words belonging to 59 neurobiologically motivated semantic categories . |
| Outcome: | The proposed metric measures word embedding quality on monolingual and cross-lingual tasks. |