Selected Publications

For a full list, see Google Scholar!

Sycophancy

1. Myra Cheng, Robert D. Hawkins, Dan Jurafsky. Accommodation and Epistemic Vigilance: A Pragmatic Account of Why LLMs Fail to Challenge Harmful Beliefs.
2. Myra Cheng, Cinoo Lee, Pranav Khadpe, Sunny Yu, Dyllan Han, Dan Jurafsky. Sycophantic AI Decreases Prosocial Intentions and Promotes Dependence.
3. Myra Cheng*, Sunny Yu*, Cinoo Lee, Pranav Khadpe, Lujain Ibrahim, Dan Jurafsky. ELEPHANT: Measuring and Understanding Social Sycophancy in LLMs. To appear at ICLR 2026. [code]
   Press coverage by MIT Technology Review, NPR, and VentureBeat.

Anthropomorphic AI Outputs

1. Myra Cheng, Sunny Yu, Dan Jurafsky. HumT DumT: Measuring and controlling human-like language in LLMs. ACL 2025. [code]

2. Myra Cheng, Su Lin Blodgett, Alicia DeVrio, Lisa Egede, Alexandra Olteanu. Dehumanizing Machines: Mitigating Anthropomorphic Behaviors in Text Generation Systems. ACL 2025 (Oral).
   ✩ SAC Highlights Award

3. Myra Cheng, Alicia DeVrio, Lisa Egede, Su Lin Blodgett, Alexandra Olteanu. “I Am the One and Only, Your Cyber BFF”: Understanding the Impact of GenAI Requires Understanding the Impact of Anthropomorphic AI. ICLR Blogposts 2025.

4. Alicia DeVrio, Myra Cheng, Lisa Egede, Alexandra Olteanu, Su Lin Blodgett. A Taxonomy of Linguistic Expressions That Contribute To Anthropomorphism of Language Technologies. CHI 2025.

AI Discourse, Public Perceptions, & Field-wide Impacts

1. Myra Cheng*, Angela Y. Lee*, Kristina Rapuano, Kate Niederhoffer, Alex Liebscher, Jeffrey Hancock. From tools to thieves: Measuring and understanding public perceptions of AI through crowdsourced metaphors. FAccT 2025.
   Press coverage by Fortune, Forbes, and New Scientist.

2. Pratyusha Ria Kalluri*, William Agnew*, Myra Cheng*, Kentrell Owens*, Luca Soldaini*, Abeba Birhane*. Computer-vision research powers surveillance technology. Nature 2025.
   Press coverage by Nature and 404 Media.

3. Lujain Ibrahim*, Myra Cheng*. Thinking beyond the anthropomorphic paradigm benefits LLM research. Under review.

4. Myra Cheng, Kristina Gligorić, Tiziano Piccardi, Dan Jurafsky. AnthroScore: A Computational Linguistic Measure of Anthropomorphism. EACL 2024. [website] [slides] [code]
   Press coverage by Scientific American and New Scientist.

Caricatures, Stereotypes, and Bias

1. Myra Cheng, Tiziano Piccardi, Diyi Yang. CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations. EMNLP 2023. [poster] [code]

2. Myra Cheng, Esin Durmus, Dan Jurafsky. Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models. ACL 2023. [slides] [code]
   ✩ Social Impact Award, Nominated for Best Paper

3. Federico Bianchi*, Pratyusha Kalluri*, Esin Durmus*, Faisal Ladhak*, Myra Cheng*, Debora Nozza, Tatsunori Hashimoto, Dan Jurafsky, James Zou, Aylin Caliskan. Easily accessible text-to-image generation amplifies demographic stereotypes at large scale. FAccT 2023.
   Press coverage by Nature, CBS News Prime Time, the Washington Post and MIT Technology Review.

4. Myra Cheng, Maria De-Arteaga, Lester Mackey, Adam Tauman Kalai. Social Norm Bias: Residual Harms of Fairness-Aware Algorithms. Data Mining and Knowledge Discovery 2023. [code]

5. Laura Weidinger, John Mellor, Maribeth Rauh, Conor Griffin, Jonathan Uesato, Po-Sen Huang, Myra Cheng et al. Ethical and Social Risks of Harm from Language Models. FAccT 2022.