activity
20242026
most citedPosition: LLM Unlearning Benchmarks are Weak Measures of Progress

1 citations · 1 across the 6 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

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…