Scholar
Sonia K. Murthy
Google Scholar ID: MFLudqMAAAAJ
Harvard University
Citations & Impact
Citations
70
H-index
4
i10-index
3
Publications
8
Co-authors
0
Contact
Publications
Resume (English only)
Academic Achievements
- - 'Inside you are many wolves: Using cognitive models to reveal value trade-offs in language models', Pragmatic Reasoning in Language Models workshop @ COLM 2025
- - 'One fish, two fish, but not the whole sea: Alignment reduces language models’ conceptual diversity', NAACL (2025)
- - 'Comparing the Evaluation and Production of Loophole Behavior in Humans and Large Language Models', EMNLP Findings (2023)
- - 'ACCoRD: A Multi-Document Approach to Generating Diverse Descriptions of Scientific Concepts', EMNLP System Demonstrations (2022)
- - 'Shades of confusion: Lexical uncertainty modulates ad hoc coordination in an interactive communication task', Cognition (2022)
- - Undergraduate thesis 'Towards a computational model of human word-color associations', Princeton University (2020)
- - NCWIT Collegiate Award Finalist (2020)
Research Experience
- - Harvard University: Working under the guidance of Tomer Ullman
- - UK AI Security Institute: As a MATS scholar, working with Tomek Korbak and others on evaluating human-AI complementarity techniques for improving scalable oversight of AI agents
- - Allen Institute for Artificial Intelligence: Previously, a Predoctoral Young Investigator on the Semantic Scholar team, working with Doug Downey and Daniel Weld on generating diverse descriptions of scientific concepts
- - Princeton Computational Cognitive Science Lab: Worked with Tom Griffiths and Robert Hawkins on models of human word-color associations and studying the mental representations that enable us to flexibly communicate
Education
- Fourth-year PhD student in Computer Science at Harvard University, advised by Tomer Ullman in the Computation, Cognition, and Development Lab. Also collaborates with Hidenori Tanaka and Ekdeep Singh Lubana in the Science of Intelligence for Alignment group. Supported by an NSF Graduate Research Fellowship and a Kempner Institute Graduate Fellowship.
Background
- Cares about understanding humans as thinking, feeling, computational machines and using these insights to build artificial intelligence that better serves a diversity of human intelligence. Current work applies models and methodologies from computational cognitive science and human-AI interaction to evaluate and improve LLMs’ abilities to be safe, flexible, and cooperative social partners. Approaches challenges in AI safety and value alignment through the lenses of pragmatic communication and theory-of-mind reasoning in humans.
Miscellany
- Feel free to reach out if you would like to chat about research or are a woman/minority student considering graduate school in Psychology or Computer Science.
Co-authors