Birdwatch Archive

Birdwatch Note Rating

2023-03-27 19:44:52 UTC - NOT_HELPFUL

Rated by Participant: B8994860E462F1A94C71F3FF7083F5A7415D66AE65A62452736A54150C709437
Participant Details

Original Note:

The post demonstrates an example of bias in ChatGPT answers. This is because machine learning models' output strongly depends on training data. The inference is that there is bias in the training data or how the training was performed. https://www.techtarget.com/searchenterpriseai/definition/machine-learning-bias-algorithm-bias-or-AI-bias

All Note Details

Original Tweet

All Information

  • noteId - 1640345172616572930
  • participantId -
  • raterParticipantId - B8994860E462F1A94C71F3FF7083F5A7415D66AE65A62452736A54150C709437
  • createdAtMillis - 1679946292596
  • version - 2
  • agree - 0
  • disagree - 0
  • helpful - 0
  • notHelpful - 0
  • helpfulnessLevel - NOT_HELPFUL
  • helpfulOther - 0
  • helpfulInformative - 0
  • helpfulClear - 0
  • helpfulEmpathetic - 0
  • helpfulGoodSources - 0
  • helpfulUniqueContext - 0
  • helpfulAddressesClaim - 0
  • helpfulImportantContext - 0
  • helpfulUnbiasedLanguage - 0
  • notHelpfulOther - 1
  • notHelpfulIncorrect - 1
  • notHelpfulSourcesMissingOrUnreliable - 1
  • notHelpfulOpinionSpeculationOrBias - 0
  • notHelpfulMissingKeyPoints - 1
  • notHelpfulOutdated - 0
  • notHelpfulHardToUnderstand - 1
  • notHelpfulArgumentativeOrBiased - 1
  • notHelpfulOffTopic - 0
  • notHelpfulSpamHarassmentOrAbuse - 1
  • notHelpfulIrrelevantSources - 0
  • notHelpfulOpinionSpeculation - 1
  • notHelpfulNoteNotNeeded - 0
  • ratingsId - 1640345172616572930B8994860E462F1A94C71F3FF7083F5A7415D66AE65A62452736A54150C709437