Explicit demographic statements trigger higher refusal rates and lower semantic similarity in LLMs than implicit dialect cues, which reduce refusals but also reduce content sanitization.
Intersectionally fair
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
PrivacyAkinator uses LLM-generated questions grounded in data-flow representations and a news-mined design space to help developers surface privacy decisions, yielding 47% more decisions identified in 73% less time than PRAM in a 24-person study.
A metadata-conditioned mT5 model trained on rule-augmented dialectal Arabic data produces translations that better match intended regional varieties than high-resource baselines, despite lower BLEU scores.
Generative LMs in laissez-faire open-ended prompting settings disproportionately generate subordinated portrayals of minoritized race, gender, and sexual orientation identities at rates hundreds to thousands of times higher than empowering ones.
A new toolkit with cards and maps enables AI designers to juxtapose values and harms in early concept stages, shown valuable in designer surveys and interviews.
citing papers explorer
-
Dialect vs Demographics: Quantifying LLM Bias from Implicit Linguistic Signals vs. Explicit User Profiles
Explicit demographic statements trigger higher refusal rates and lower semantic similarity in LLMs than implicit dialect cues, which reduce refusals but also reduce content sanitization.
-
PrivacyAkinator: Articulating Key Privacy Design Decisions by Answering LLM-Generated Multiple-choice Questions
PrivacyAkinator uses LLM-generated questions grounded in data-flow representations and a news-mined design space to help developers surface privacy decisions, yielding 47% more decisions identified in 73% less time than PRAM in a 24-person study.
-
Context-Aware Dialectal Arabic Machine Translation with Interactive Region and Register Selection
A metadata-conditioned mT5 model trained on rule-augmented dialectal Arabic data produces translations that better match intended regional varieties than high-resource baselines, despite lower BLEU scores.
-
Laissez-Faire Harms: Algorithmic Biases in Generative Language Models
Generative LMs in laissez-faire open-ended prompting settings disproportionately generate subordinated portrayals of minoritized race, gender, and sexual orientation identities at rates hundreds to thousands of times higher than empowering ones.
-
Developing an AI Concept Envisioning Toolkit to Support Reflective Juxtaposition of Values and Harms
A new toolkit with cards and maps enables AI designers to juxtapose values and harms in early concept stages, shown valuable in designer surveys and interviews.