AI RESEARCH
Option-Order Randomisation Reveals a Distributional Position Attractor in Prompted Sandbagging
arXiv CS.AI
•
ArXi:2604.26206v1 Announce Type: cross A predecessor pilot (Cacioli, 2026) found that Llama-3-8B implements prompted sandbagging as positional collapse rather than answer avoidance. However, fixed option ordering in MMLU-Pro left open whether this reflected a model-level position-dominant policy or dataset-level distractor structure. This pre-registered follow-up (3 models, 2,000 MMLU-Pro items, 4 conditions, 24,000 primary trials) added cyclic option-order randomisation as the critical control.