Book
Open access
Jul 2026
From Existence to Exhaustiveness: Unveiling the Compounding Failures of LLMs in Multi-answer Event Temporal Reasoning
MulTR, a comprehensive benchmark designed for multi-answer temporal reasoning from long unstructured contexts, is introduced, designed to systematically decouple temporal reasoning capabilities from the uncertainty of the number of answers.
Shaojuan Wu
· Annual International ACM SIG... · 0 citations