Year: 2024
Type: preprint
Abstract: Given the black-box nature and complexity of large transformer language models (LM), concerns about generalizability and robustness present ethical implications for domains such as hate speech (HS) detection. Using the content rich Social Bias Frames dataset, containing human-annotated stereotypes, intent, and targeted groups, we develop a three stage analysis to evaluate if LMs faithfully assess hate speech. First, we observe the need for modeling contextually grounded stereotype intents to capture implicit semantic meaning. Next, we design a new task, Stereotype Intent Entailment (SIE), which encourages a model to contextually understand stereotype presence. Finally, through ablation tests and user studies, we find a SIE objective improves content understanding, but challenges remain in modeling implicit intent.
Source: arXiv (Cornell University)
Authors: Chen, Jennifer L., Ladhak, Faisal, Li, Daniel, Elhadad, Noémie
Institution: Columbia University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4404391025