Parameter-Efficient Transfer Learning for NLP

On the reading lists

• #308 in the Top 500 (2026 edition)
• #37 in Deep learning (2026 edition)

Why it matters

Established task-specific adapter modules as an effective alternative to full model fine-tuning.

Condensed from the expert lists' notes.

The record

First released

2019 (from arXiv 1902.00751)

Citations

7,563 citations, as counted by Papers With Code (CC BY-SA 4.0)

Named by

both expert lists

Also relevant to

Language, speech & LLMs

Score

0.439 · computed rank 308 · consensus 0.58, must-read 0, citations percentile 0.756 (2010s · deep-learning), awards 0, existing lists 0. Method