Language, speech & LLMs· 2019
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
On the reading lists
- #78 in the Top 500 (2026 edition)
- #13 in Language, speech & LLMs (2026 edition)
Why it matters
Introduced T5, unifying diverse NLP tasks under text-to-text transfer learning.
Condensed from the expert lists' notes.
The record
- First released
- 2019 (from arXiv 1910.10683)
- Citations
- 27,780 citations, as counted by Papers With Code (CC BY-SA 4.0)
- Named by
- both expert lists
- Score
- 0.692 · computed rank 78 · consensus 0.86, must-read 1, citations percentile 0.956 (2010s · language), awards 0, existing lists 0. Method
Editor's notes
- Readability check: fail: A 67-page empirical study; its key ideas are covered by BERT and GPT-3 for a learner. (AI draft (Claude), not yet reviewed, 2026-10-29)
Data sources
Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0). Each count names its source. See the method.