2 papers
cs.CL2025
EMBRACE: Shaping Inclusive Opinion Representation by Aligning Implicit Conversations with Social Norms
Abeer Aldayel, Areej Alokaili
Shaping inclusive representations that embrace diversity and ensure fair participation and reflections of values is at the core of many conversation-based models. However, many exi…
cs.CL2024
Covert Bias: The Severity of Social Views' Unalignment in Language Models Towards Implicit and Explicit Opinion
Abeer Aldayel, Areej Alokaili, Rehab Alahmadi
While various approaches have recently been studied for bias identification, little is known about how implicit language that does not explicitly convey a viewpoint affects bias am…