Eve Fleisig

I'm a third-year PhD student at UC Berkeley, advised by Rediet Abebe and Dan Klein. My research lies at the intersection of natural language processing (NLP) and ethical AI: how can we create NLP systems that we trust to work for all users, without perpetuating societal harms? Specifically, I have worked on measuring & mitigating harms in text generated by LLMs, improving evaluation, and training models that account for different user perspectives or data annotators who disagree.

​

I did my undergraduate work at Princeton University, advised by Christiane Fellbaum, where I worked on the psycholinguistics of bilingualism and fairness in NLP.

​

My research is supported by an NSF Graduate Research Fellowship.

​

Selected Work

Please see Google or Semantic Scholar for an up-to-date publication list.

​

When the Majority is Wrong: Modeling Annotator Disagreement for Subjective Tasks

Eve Fleisig, Rediet Abebe, Dan Klein (EMNLP 2023).

[ ARXIV ]  [ TWITTER ] 

​

Incorporating Worker Perspectives into MTurk Annotation Practices for NLP

Olivia Huang, Eve Fleisig, Dan Klein (EMNLP 2023 - Outstanding Paper Award).

[ ARXIV ]

​

Ghostbuster: Detecting Text Ghostwritten by Large Language Models

Vivek Verma, Eve Fleisig, Nicholas Tomlin, Dan Klein

[ ARXIV ]  [ TWITTER ]  [ BLOG ]

​

Hedges and Apologies in ChatGPT Responses to African-American English

Eve Fleisig (NWAV 2023).

[ SLIDES ] [ ABSTRACT ]

​

First Tragedy, then Parse: History Repeats Itself in the New Era of Large Language Models

Naomi Saphra, Eve Fleisig, Kyunghyun Cho, Adam Lopez

[ ARXIV ]  [ TWITTER ]

​

Centering the Margins: Outlier-Based Identification of Harmed Populations in Toxicity Detection

Vyoma Raman*, Eve Fleisig*, Dan Klein (EMNLP 2023).

[ ARXIV ]  [ TWITTER ] 

​

FairPrism: Evaluating fairness-related harms in text generation

Eve Fleisig, Aubrie Amstutz, Chad Atalla, Su Lin Blodgett, Hal Daumé III, Alexandra Olteanu, Emily Sheng, Dan Vann, Hanna Wallach (ACL 2023).

[ PAPER ]  [ DATASET ] 

​

Mitigating Gender Bias in Machine Translation through Adversarial Learning

Eve Fleisig, Christiane Fellbaum
Outstanding Senior Thesis Award; Sigma Xi Book Award

[ ARXIV ]

​

Mentorship

I've mentored some wonderful undergraduate students, including Harbani Jaggi, Kayla Lee, Kashyap Murali, Mahathi Ryali, Zaina Shaik, Vivek Verma, Xavier Yin, Olivia Huang (→Citadel), and Vyoma Raman (→Stanford).

​

If you are an undergraduate interested in working together, please email me your resume, a description of your interests, and why you're interested in working with me.

​

Interested in chatting or collaborating? 

Reach out to me at efleisig :at: berkeley :dot: edu

​

Miscellaneous

My surname is pronounced /'flʌɪsɪg/ ("fly"-sihg).

🇦🇷¡Siempre estoy feliz de charlar con otros latinoamericanos!

​