Skip to main content
Ctrl+K

StrongREJECT documentation

  • API reference
  • GitHub
  • API reference
  • GitHub

Section Navigation

  • Datasets
  • Apply jailbreaks
  • Generate responses
  • Evaluate responses
  • API reference

API reference#

  • Datasets
    • load_strongreject()
    • load_strongreject_small()
    • load_wmdp_open_ended()
  • Apply jailbreaks
    • apply_jailbreaks()
    • apply_jailbreaks_to_dataset()
    • auto_obfuscation()
    • auto_payload_splitting()
    • decode()
    • decode_dataset()
    • disemvowel()
    • pair()
    • pap()
    • register_decoder()
    • register_jailbreak()
    • rot_13()
    • translate()
    • wrapping_jailbreak()
  • Generate responses
    • convert_to_messages()
    • generate()
    • generate_to_dataset()
  • Evaluate responses
    • accuracy_rubric()
    • category_binary()
    • evaluate()
    • evaluate_dataset()
    • gpt4_judge()
    • harmbench()
    • jailbroken_binary()
    • openai_moderation_api()
    • pair()
    • register_evaluator()
    • string_matching()
    • strongreject_aisi()
    • strongreject_finetuned()
    • strongreject_rubric()

previous

StrongREJECT documentation

next

strong_reject.load_datasets

This Page

  • Show Source

© Copyright 2024, Dillon Bowen.

Created using Sphinx 8.1.3.

Built with the PyData Sphinx Theme 0.16.1.