3 papers
cs.AI2026
Personalization, Personas, and Forecasting in Value Alignment
James Wedgwood, Pratiksha Thaker, Neil Kale +1
LLM behavior may be conditioned by human identity in several ways: they may be asked to adapt to users, role-play populations, or forecast how people would answer value-laden quest…
cs.LG2026
DSPA: Dynamic SAE Steering for Data-Efficient Preference Alignment
James Wedgwood, Aashiq Muhamed, Mona T. Diab +1
Preference alignment is usually achieved by weight-updating training on preference data, which adds substantial alignment-stage compute and provides limited mechanistic visibility.…
cs.CL2026
Automated Concept Discovery for LLM-as-a-Judge Preference Analysis
James Wedgwood, Chhavi Yadav, Virginia Smith
Large Language Models (LLMs) are increasingly used as scalable evaluators of model outputs, but their preference judgments exhibit systematic biases and can diverge from human eval…