WikiFact

Scenario introduced in this work, inspired by Petroni et al. (2019), to more extensively test factual knowledge.

  • Task: knowledge base completion
  • What: entity-relation-entity triples in natural language form
  • When: ?
  • Who: automatically generated from templates
  • Language: structured English
  1. EM

  2. Denoised inference time (s)

  3. # eval

  4. # train

  5. truncated

  6. # prompt tokens

  7. # output tokens

  8. # trials