evaluation-task · Source-linked discovery
AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions
Evaluating abstention across 20 diverse datasets, including questions with unknown answers, underspecification, false premises, subjective interpretations, and outdated information.
OriginPolina Kirichenko, Mark Ibrahim, Kamalika Chaudhuri et al.TopicsEvaluation integrityStatusimported
Can support
Not independently assessed by FronteraEval yet.
Cannot support by itself
No inference beyond the upstream source should be made until the protocol is reviewed.