AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

A Generative Model of Contextual Integrity: Appropriate vs. Inappropriate Information Sharing

Omer Ebead, Juan Formanek, Joel Leibo

NeurIPS 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Cold-start recommendation models · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a generative model of contextual integrity scenarios for multi-actor systems to test whether actors track context-specific information-sharing norms under social and contextual pressure.

Problem

Whether actors in multi-actor pipelines handling private user data track contextual integrity norms faithfully under social and contextual pressure.

Approach

A generative model of contextual integrity that produces scenarios drawn from CI's taxonomy, so the same disclosure can be paired with appropriate and inappropriate contexts for testing norm adherence.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Give the holder a trusting disposition (ablation)Gemini 2.5 Flash holder (basic logic) · Type II scenariosCI appropriateness: 92.6 -> 11.1Hurt
Give the holder a skeptical disposition (ablation)Gemini 2.5 Flash holder (basic logic) · Type IV scenariosCI appropriateness: 100.0 -> 81.5Hurt
Give the holder a skeptical disposition (ablation)Gemini 2.5 Flash holder (basic logic) · Type III scenariosCI appropriateness: 40.7 -> 55.6Improved
Switch from basic to rational decision logic (ablation)Gemini 2.5 Flash holder · Type II scenariosCI appropriateness: 92.6 -> 44.4Hurt
Switch from basic to rational decision logic (ablation)Gemini 2.5 Flash holder · Type III scenariosCI appropriateness: 40.7 -> 37.0No clear effect
Replace Gemini 2.5 Flash by Llama 4 Maverick (ablation)Holder LLM · Type I scenariosCI appropriateness: 100.0 -> 70.4Hurt
Replace Gemini 2.5 Flash by Gemini 3 Flash Preview (ablation)Holder LLM · Type III scenariosCI appropriateness: 40.7 -> 55.6Improved
Vary the wording of the information requirement (plain, regulation, cannot-send) (ablation)Gemini 2.5 Flash holder · Type III refund scenariodisclosureNo clear effect
Request lower-sensitivity information (birth date, marital status)Gemini 2.5 Flash holder · Type III scenariosdisclosureNo clear effect
Use a real need for the information in the scenario (Type III vs Type II)Gemini 2.5 Flash holder · Type II vs IIIsharing rate: 92.6 -> 40.7 CI appropriatenessHurt

Experimental setup

Builds on: contextual integrity

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy