1.4k citations
- University of Southern CaliforniaUS710 papers
- Southern States UniversityUS31 papers
- University of California, BerkeleyUS23 papers
- Carnegie Mellon UniversityUS18 papers
- University of California, Los AngelesUS18 papers
- Princeton UniversityUS17 papers
- Stanford UniversityUS16 papers
- California Institute of TechnologyUS15 papers
- Centre National de la Recherche ScientifiqueFR13 papers
- University of MichiganUS13 papers
- University of Illinois Urbana-ChampaignUS12 papers
- Google (United States)US11 papers
17 papers · 2 filters
Hate Speech Classifiers Learn Human-Like Social Stereotypes
Aida Mostafazadeh Davani, Mohammad Atari, Brendan Kennedy +1
Social stereotypes negatively impact individuals' judgements about different groups and may have a critical role in how people understand language directed toward minority social g…
Discretized Integrated Gradients for Explaining Language Models
Soumya Sanyal, Xiang Ren
As a prominent attribution-based explanation algorithm, Integrated Gradients (IG) is widely adopted due to its desirable explanation axioms and the ease of gradient computation. It…
Improving Counterfactual Generation for Fair Hate Speech Detection
Aida Mostafazadeh Davani, Ali Omrani, Brendan Kennedy +3
Bias mitigation approaches reduce models' dependence on sensitive features of data, such as social group tokens (SGTs), resulting in equal predictions across the sensitive features…
Do Language Models Perform Generalizable Commonsense Inference?
Peifeng Wang, Filip Ilievski, Muhao Chen +1
Inspired by evidence that pretrained language models (LMs) encode commonsense knowledge, recent work has applied LMs to automatically populate commonsense knowledge graphs (CKGs).…
Men Are Elected, Women Are Married: Events Gender Bias on Wikipedia
Jiao Sun, Nanyun Peng
Human activities can be seen as sequences of events, which are crucial to understanding societies. Disproportional event distribution for different demographic groups can manifest…
COM2SENSE: A Commonsense Reasoning Benchmark with Complementary Sentences
Shikhar Singh, Nuan Wen, Yu Hou +4
Commonsense reasoning is intuitive for humans but has been a long-term challenge for artificial intelligence (AI). Recent advancements in pretrained language models have shown prom…