prediction-flips

Tag

Cards List
#prediction-flips

The Illusion of Robustness: Aggregate Accuracy Hides Prediction Flips under Task-Irrelevant Context

arXiv cs.CL · 2026-07-15 Cached

This paper reveals that while large language models appear robust to task-irrelevant context at the aggregate level, their predictions can flip on individual examples, with performance degrading on some and improving on others, highlighting tail risks that aggregate accuracy conceals.

0 favorites 0 likes
← Back to home

Submit Feedback