Profiles2021-2023
Sharon Levy
University of California
8Papers
0Last author
20Unique co-authors
3First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers8
- ASSERT: Automated Safety Scenario Red Teaming for Evaluating the Robustness of Large Language ModelsAuthor 2 of 3EMNLP Findings 2023 · 9 citations
- Comparing Biases and the Impact of Multilingual Training across Multiple LanguagesAuthor 1 of 9EMNLP 2023 · 9 citations
- Foveate, Attribute, and Rationalize: Towards Physically Safe and Trustworthy AIAuthor 2 of 3ACL Findings 2023 · 3 citations
- SafeText: A Benchmark for Exploring Physical Safety in Language ModelsAuthor 1 of 7EMNLP 2022 · 14 citations
- HybriDialogue: An Information-Seeking Dialogue Dataset Grounded on Tabular and Textual DataAuthor 2 of 5ACL Findings 2022 · 13 citations
- Mitigating Covertly Unsafe Text within Natural Language SystemsAuthor 3 of 10EMNLP Findings 2022 · 2 citations
- Investigating Memorization of Conspiracy Theories in Text GenerationAuthor 1 of 3ACL Findings 2021 · 10 citations
- Modeling Disclosive Transparency in NLP Application DescriptionsAuthor 2 of 5EMNLP 2021 · 3 citations
