Scaling Instruction-Finetuned Language Models

Explore this paper's citation graph

Summary

It is found that instruction finetuning with the above aspects dramatically improves performance on a variety of model classes (PaLM, T5, U-PaLM), prompting setups, and evaluation benchmarks (MMLU, BBH, TyDiQA, MGSM, open-ended generation).

Type
preprint
Published
2022-10-20
Cited by
4,394
References
106
Access
Open access

Keywords

Computer science, Margin (machine learning), Usability, Variety (cybernetics), Scaling

References

Cited by

Related papers