Publications: 'Semantic Regexes: Auto-Interpreting LLM Features with a Structured Language', 'Abstraction Alignment: Comparing Model-Learned and Human-Encoded Conceptual Relationships', etc.; Awards: Outstanding Paper Award at ACL 2023; Honors: MIT John Jarve Fellowship, Apple Scholars in AI/ML PhD Fellowship.
Research Experience
During her PhD at MIT, interned at Apple Research with Fred Hohman and IBM Research with Hendrik Strobelt.
Education
PhD: MIT CSAIL, Advisor: Arvind Satyanarayan; SB and MEng: MIT, Advisors: Jim Glass and David Harwath.
Background
Research Interests: Improving human-AI alignment by designing systems that reveal model representations and methods to shift them toward human expectations. Field: HCI + AI.