I am a computational linguist and an assistant professor of Computer Science at Wellesley College.


My research focuses on understanding how context-sensitive meaning is encoded in natural language. I build computational models to understand how conversation participants use knowledge about each other's mental states. How do speakers think about their audience when deciding what to say? How do listeners use their knowledge of the speaker when figuring out the meaning of their utterances?

More recently, I have been focusing on evaluating large language models for natural language and code generation. What are the abilities and limitations of LLMs? Can LLMs help non-expert programmers? I study these questions from a variety of angles, including model development, benchmarking and evaluation, and human-computer interaction studies.

carolyn.anderson AT wellesley.edu


o February 2023: I visited Swarthmore to give a colloquium in the Linguistics department

o February 2023: Parenthesized Modifiers in English and Korean: What They (May) Mean accepted to ELM 3

o January 2023: How Beginning Programmers and Code LLMs (Mis)read Each Other accepted to CHI 2024

o January 2023: Can It Edit? accepted to LLM4Code workshop at ICSE 2024

o January 2023: StudentEval accepted to LLM4Code workshop at ICSE 2024

o November 2023: StarCoder accepted to Transactions on Machine Learning Research

o November 2023: Three papers by EASEL lab alums presented at TADA 2023

o September 2023: Protagonist-Mediated Perspective presented at Sinn und Bedeutung 28.

o August 2023: Received an NSF Award for research on Code LLMs for programming in the sciences, with Molly Q Feldman, Arjun Guha, and Erin G. Teich