iCreatAI News
Skip to content
Trending storyUpdating

Mizan releases benchmark on word bias in the Israeli-Palestinian context

1 reports1 sources18 hr agoUpdated

Understand this story

AI overview

Tech for Palestine's Mizan project has released an AI bias benchmark that tests whether models use terminology consistently on the Israeli-Palestinian issue. The test uses the same passage describing people held without charge, changing only the nationality and the detaining party, and asks 16 AI models to choose among the four words hostage, prisoner, detainee, and captive, collecting a total of 3,072 responses. The project's goal is to examine the fairness of models on the Israeli and Palestinian issue; the test results have not yet been given in the report.

AI overview based on source reports · Updated 18 hr ago

Coverage timeline

Follow the coverage to explore different perspectives.

Nov 17
  1. Hacker News AI
    Mizan bias benchmark: testing AI models

    Tech for Palestine's Mizan project tested 16 AI models with identical scenarios of a person held without charge, varying only nationality and captor, and found most models chose "hostage" for Israelis but "detainee" for Palestinians. Anthropic's Claude models did this almost every time, OpenAI's were slightly better, and Google's Gemini scored higher mainly by refusing to answer most requests. The piece also cites Adam H. Johnson's How to Sell a Genocide and Assal Rad's Don't Say Palestine on media word choices.

Activity for this story

Current comparable activity
6
Peak comparable activity
10Nov 17 16:00
Change in the past 24 hours
–

Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.