Emily Sheng

Computer Science · Physical Sciences

10h-index794citations34works0.32yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

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

Research Topics

Topic Modeling(18), Natural Language Processing Techniques(12), Hate Speech and Cyberbullying Detection(10), Sentiment Analysis and Opinion Mining(5), Social Media and Politics(3)

Publications34 total

Understanding and Meeting Practitioner Needs When Measuring Representational Harms Caused by LLM-Based Systems
arXiv (Cornell University)·2025Open Access
Taxonomizing Representational Harms using Speech Act Theory
arXiv (Cornell University)·2025Open Access
Position: Evaluating Generative AI Systems Is a Social Science Measurement Challenge
arXiv (Cornell University)·2025Open Access
Understanding and Meeting Practitioner Needs When Measuring Representational Harms Caused by LLM-Based Systems
2025Open Access
Taxonomizing Representational Harms using Speech Act Theory
2025· 1 citedOpen Access
A Shared Standard for Valid Measurement of Generative AI Systems' Capabilities, Risks, and Impacts
arXiv (Cornell University)·2024Open Access
Gaps Between Research and Practice When Measuring Representational Harms Caused by LLM-Based Systems
arXiv (Cornell University)·2024· 1 citedOpen Access
Evaluating Generative AI Systems is a Social Science Measurement Challenge
arXiv (Cornell University)·2024Open Access
A Framework for Automated Measurement of Responsible AI Harms in Generative AI Applications
arXiv (Cornell University)·2023· 1 citedOpen Access
FairPrism: Evaluating Fairness-Related Harms in Text Generation
2023· 9 citedOpen Access
A Keyword Based Approach to Understanding the Overpenalization of Marginalized Groups by English Marginal Abuse Models on Twitter
2023· 1 citedOpen Access
A Keyword Based Approach to Understanding the Overpenalization of Marginalized Groups by English Marginal Abuse Models on Twitter
arXiv (Cornell University)·2022· 2 citedOpen Access
On Measures of Biases and Harms in NLP
2022· 37 citedOpen Access
NERO: a biomedical named-entity (recognition) ontology with a large, annotated corpus reveals meaningful associations through text embedding
npj Systems Biology and Applications·2021· 13 citedOpen Access
On Measures of Biases and Harms in NLP
arXiv (Cornell University)·2021· 9 citedOpen Access
What do Bias Measures Measure
arXiv (Cornell University)·2021· 5 citedOpen Access
Societal Biases in Language Generation: Progress and Challenges
arXiv (Cornell University)·2021· 12 citedOpen Access
Revealing Persona Biases in Dialogue Systems
arXiv (Cornell University)·2021· 20 citedOpen Access
“Nice Try, Kiddo”: Investigating Ad Hominems in Dialogue Responses
2021· 37 citedOpen Access
Societal Biases in Language Generation: Progress and Challenges
2021· 108 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Kai-Wei Chang(13), Nanyun Peng(13), Prem Natarajan(12), Hanna Wallach(10), Alexandra Chouldechova(8), Jean Garcia-Gathright(8), Chad Atalla(7), Dan Vann(7), Su Lin Blodgett(6), Alexandra Olteanu(6), Emily Corvi(5), Hannah Washington(5), Seann Reed(5), P. Alex Dow(5), Nicholas Pangakis(5), Max Vogel(5), Jonathan Gordon(4), Sunipa Dev(3), Jieyu Zhao(3), Aubrie Amstutz(3)