Atlas reaches over 42% accuracy on Natural Questions with only 64 examples, outperforming a 540B-parameter model by 3% with 50x fewer parameters.
Robust Disambiguation of Named Entities in Text
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2022 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Atlas: Few-shot Learning with Retrieval Augmented Language Models
Atlas reaches over 42% accuracy on Natural Questions with only 64 examples, outperforming a 540B-parameter model by 3% with 50x fewer parameters.