Symbol tuning improves in-context learning in language modelsbb
| Jan 23, 2024
0  |  Read Time 0 min
link
Publish Date
Number
reflection
abstract
propose symbol tuning, which involves fine-tuning a language model using input-label mapping unrelated to semantic prior. They aim to investigate whether LLMs can induce input-label patterns when performing unseen in-context learning tasks and further improve reasoning abilities.
Status
Done
Type
improving
Author
  • Valine
Catalog