WORTH Benchmark: Evidence Discovery under Not-Fully-Cooperative Information -- A Two-Episode Pilot
The WORTH Benchmark is proposed: models read original mystery narratives without clue annotations, autonomously select key clue sentences, identify case participants, and explain their reasoning process, and it is suggested that not-fully-cooperative informational relationships may influence evidence selection and judg...
B. Zou, Chao Xu
· 0 citations