Alicia Parrish

Google (United States) — United States

Computer Science · Physical Sciences

14h-index2.7kcitations58works25.52yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Topic Modeling(24), Natural Language Processing Techniques(23), Speech and dialogue systems(7), Reading and Literacy Development(5), Neurobiology of Language and Bilingualism(5)

Publications55 total

Risk Management for Mitigating Benchmark Failure Modes: BenchRisk
arXiv (Cornell University)·2025Open Access
"Just a Strange Pic": Rethinking 'Safety' in GenAI Image Safety Annotation Tasks from Diverse Annotators' Perspectives
Proceedings of the AAAI/ACM Conference on AI Ethics and Society·2025Open Access
From Seed to Harvest: Augmenting Human Creativity with AI for Red-teaming Text-to-Image Models
arXiv (Cornell University)·2025Open Access
"Just a strange pic": Evaluating 'safety' in GenAI Image safety annotation tasks from diverse annotators' perspectives
arXiv (Cornell University)·2025Open Access
Whose View of Safety? A Deep DIVE Dataset for Pluralistic Alignment of Text-to-Image Models
ArXiv.org·2025· 1 citedOpen Access
Changes in auditory evoked responses at different levels of linguistic processing in adults and school-age children: An MEG study
Neuropsychologia·2025· 1 cited
Decoding Safety Feedback from Diverse Raters: A Data-driven Lens on Responsiveness to Severity
arXiv (Cornell University)·2025Open Access
MSTS: A Multimodal Safety Test Suite for Vision-Language Models
arXiv (Cornell University)·2025Open Access
Insights on Disagreement Patterns in Multimodal Safety Perception across Diverse Rater Groups
arXiv (Cornell University)·2024Open Access
A toolbox for surfacing health equity harms and biases in large language models
Nature Medicine·2024· 63 citedOpen Access
Gemma 2: Improving Open Language Models at a Practical Size
arXiv (Cornell University)·2024· 125 citedOpen Access
Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image Generation
2024· 6 citedOpen Access
Introducing v0.5 of the AI Safety Benchmark from MLCommons
arXiv (Cornell University)·2024· 5 citedOpen Access
A Toolbox for Surfacing Health Equity Harms and Biases in Large Language Models
arXiv (Cornell University)·2024· 6 citedOpen Access
Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image Generation
arXiv (Cornell University)·2024Open Access
Developmental Changes in Auditory Evoked Responses at Different Levels of Linguistic Processing: An Meg Study
SSRN Electronic Journal·2024Open Access
GRASP: A Disagreement Analysis Framework to Assess Group Associations in Perspectives
2024· 4 citedOpen Access
DMLR: Data-centric Machine Learning Research -- Past, Present and Future
TU/e Research Portal·2023· 6 citedOpen Access
GRASP: A Disagreement Analysis Framework to Assess Group Associations in Perspectives
arXiv (Cornell University)·2023Open Access
MEG correlates of speech planning in simple vs. interactive picture naming in children and adults
PLoS ONE·2023· 1 citedOpen Access
page 1 of 3Next →

Frequent Co-authors

Samuel R. Bowman(17), Jason Phang(14), Lora Aroyo(13), Nikita Nangia(11), Alex Warstadt(9), Mark Díaz(9), Vinodkumar Prabhakaran(8), Charvi Rastogi(7), Haokun Liu(6), Anhad Mohananey(6), Wei Peng(6), Sheng‐Fu Wang(6), Vishakh Padmakumar(6), Phu Mon Htut(5), Liina Pylkkänen(5), Jana Thompson(4), Samuel Bowman(4), Paloma Jeretič(4), Richard Yuanzhe Pang(4), Ethan Perez(4)