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datasets, including questions with unknown answers, underspecification, false premises, subjective interpretations, and outdated information.

Open interactive record →
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.

Original sources