Loading
Language models give answers shaped by their own values, without disclosing this influence, which can be problematic for practical questions. This covert value leakage affects the information they provide. We don't know yet whether this holds up outside the benchmark
“arXiv:2607.14345v2 Announce Type: replace-cross Abstract: People use language models for practical questions whose answers are difficult to verify. We show that models exhibit covert value leakage: the information they provide is influenced…”
Read the source →STATUS
ACTIVE
CATEGORY
Models
EVIDENCE
Not yet assessed
ENTITY
arXiv:2607.14345v2, Value Leakage
DECISION
Automated · no editorial override
LAST OBSERVED
Aug 4, 2026