Pith. sign in

Stop measuring calibration when humans disagree

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

support 1

representative citing papers

Improving LoRA with Variational Learning

cs.LG · 2025-06-17 · conditional · novelty 5.0

Replacing AdamW with IVON and pruning 10% of highest-variance LoRA parameters improves average commonsense-reasoning accuracy by 1.3 points and calibration by 5.4 points on Llama-3.2-3B.

citing papers explorer

Showing 1 of 1 citing paper.

  • Improving LoRA with Variational Learning cs.LG · 2025-06-17 · conditional · none · ref 1

    Replacing AdamW with IVON and pruning 10% of highest-variance LoRA parameters improves average commonsense-reasoning accuracy by 1.3 points and calibration by 5.4 points on Llama-3.2-3B.