WMIP: A Working-Memory-Inspired Programmable Probe of Cumulative State Tracking in Large Language Models
This work introduces a working-memory-inspired probe of cumulative state tracking with program-computed answers, 3 to 100 updates, and final-state, intermediate-state, or multi-target queries and compares protocols on identical items.
Deng-Zhe Hou, Ling-Yu Jiang, Deng-Jie Li et al.
· 5 citations