A new multi-hop false-premise benchmark shows that leading large language models detect embedded falsehoods in only a minority of cases, with the best model reaching about 23% on the full two-stage protocol.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MultiHoax: A Dataset of Multi-hop False-Premise Questions
A new multi-hop false-premise benchmark shows that leading large language models detect embedded falsehoods in only a minority of cases, with the best model reaching about 23% on the full two-stage protocol.