Showing 2026Show all
2 papers · 1 filter
cs.CL2026
SteerCheck: Attribution Specificity and Alignment Leakage in Activation-Steering Audits
Daming Luo, Christy Liang, Junyu Xuan
Activation steering can change behaviour without establishing that the effect is specific to the intended concept. We introduce SteerCheck, a preregistered attribution audit that m…
cs.LG2026
How Query Visibility Changes KV-Cache Compression Rankings: A Matched-Budget Audit
Daming Luo, Christy Liang, Junyu Xuan
KV-cache compression methods are predominantly evaluated with the query appended to the context before compression -- a query-aware protocol. Yet the economic case for a compressed…