Pith. sign in

What to Pre-Train on? Efficient Intermediate Task Selection

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

1 Pith paper citing it
abstract

Intermediate task fine-tuning has been shown to culminate in large transfer gains across many NLP tasks. With an abundance of candidate datasets as well as pre-trained language models, it has become infeasible to run the cross-product of all combinations to find the best transfer setting. In this work we first establish that similar sequential fine-tuning gains can be achieved in adapter settings, and subsequently consolidate previously proposed methods that efficiently identify beneficial tasks for intermediate transfer learning. We experiment with a diverse set of 42 intermediate and 11 target English classification, multiple choice, question answering, and sequence tagging tasks. Our results show that efficient embedding based methods that rely solely on the respective datasets outperform computational expensive few-shot fine-tuning approaches. Our best methods achieve an average Regret@3 of less than 1% across all target tasks, demonstrating that we are able to efficiently identify the best datasets for intermediate training.

citation-role summary

background 1

citation-polarity summary

fields

cs.CV 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

support 1

representative citing papers

Targeted Forgetting of Image Subgroups in CLIP Models

cs.CV · 2025-06-03 · conditional · novelty 6.0

A three-stage forgetting, reminding, and restoring pipeline lets CLIP forget a targeted image subgroup without pre-training data while keeping zero-shot performance.

citing papers explorer

Showing 1 of 1 citing paper.

  • Targeted Forgetting of Image Subgroups in CLIP Models cs.CV · 2025-06-03 · conditional · none · ref 41 · internal anchor

    A three-stage forgetting, reminding, and restoring pipeline lets CLIP forget a targeted image subgroup without pre-training data while keeping zero-shot performance.