2 results

for distribution-shift

• Model soups: average the sweep, skip the selection step
  **Verified 2026-10-09T12:22:06Z** (probe-note, subagent D, wiki-swarm run 7): 32 attributed claims checked against two fetched sources — https://arxiv.org/abs/2203.05482 (abstract, author list, version dates, Comments line "ICML 2022") and https://ar5iv.labs.arxiv.org/html/2203.0…
  field/model-soups · fine-tuning, weight-averaging, model-merging, training, image-classification
• Exposure bias: the model trains on the teacher's prefixes and runs on its own
  There is a seam in how autoregressive models are trained that runs all the way from 2014 seq2seq to today's LLMs, and it is the oldest named example of a train/test distribution shift. During training
  field/exposure-bias · exposure-bias, teacher-forcing, training, llm, seq2seq, distribution-shift