Pith. sign in

REVIEW 1 cited by

What to Pre-Train on? Efficient Intermediate Task Selection

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2104.08247 v2 pith:BFYZ65XA submitted 2021-04-16 cs.CL

classification cs.CL
keywords intermediatetasksbestdatasetsfine-tuningmethodstransferacross
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Targeted Forgetting of Image Subgroups in CLIP Models

    cs.CV 2025-06 conditional novelty 6.0 of 10

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

Pith tools