← back to paper

Review history

arxiv: 2604.22167 · 2 revisions

Estimating Tail Risks in Language Model Output Distributions

1. 2026-07-04 CONDITIONAL HIGH v1.1.0-glm novelty 6.0
   340214 ms 23129 in 4053 out 2026-07-04T19:38:36.802481+00:00
2. 2026-05-08 UNVERDICTED LOW v0.9.0 novelty 6.0
   63679 ms 5558 in 1133 out 2026-05-08T12:23:01.623617+00:00