Language, speech & LLMs· 2021
RoFormer: Enhanced Transformer with Rotary Position Embedding
DOI 10.1016/j.neucom.2023.127063arXiv 2104.09864OpenAlex W4388979610
On the reading lists
- #252 in the Top 500 (2026 edition)
- #40 in Language, speech & LLMs (2026 edition)
Why it matters
Introduced RoPE, a positional representation adopted throughout modern decoder-only LLM architectures.
Condensed from the expert lists' notes.
The record
- First released
- 2021 (from arXiv 2104.09864)
- Citations
- 6,815 citations, as counted by Papers With Code (CC BY-SA 4.0)
- Named by
- both expert lists
- Score
- 0.482 · computed rank 252 · consensus 0.59, must-read 0.5, citations percentile 0.729 (2020s · language), awards 0, existing lists 0. Method
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.