AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Operationalizing Data Minimization for Privacy-Preserving LLM Prompting

Jijie Zhou, Niloofar Mireshghallah, Tianshi Li

ICLR 2026 · Large language models › Language, safety and interpretability · approach: LLM unlearning and benchmarks · 12 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
mask spans (name) via minimizationdata minimization · WildChat type-wise recoveryHit@1 %: 90.3 -> 0.0Improved
mask geolocation spansdata minimization · WildChat type-wise recoveryHit@1 %: 89.8 -> 2.2Improved
mask occupation spansdata minimization · WildChat type-wise recoveryHit@1 %: 85.4 -> 8.0Improved
mask affiliation spansdata minimization · WildChat type-wise recoveryHit@1 %: 83.0 -> 1.9Improved
use abstraction instead of redactionminimized prompts · span-wise recoveryp_corr: 5.6--14.9% vs 2.7--7.7%Hurt
use larger frontier response model (gpt-5 vs qwen2.5-0.5b) on open-ended tasksdata minimization oracle · open-endedoptimal REDACT %: 19.3% -> 85.7%Improved
use larger model on closed-ended tasks (gpt-4.1 vs qwen2.5-0.5b)data minimization oracle · closed-endedoptimal REDACT %: 32.1% -> 98.0%Improved
replace zero-shot o3 judge with finetuned Qwen2.5-7B comparatorprivacy comparator · human-label alignmentlatency (s): 6.37 -> 0.31Improved
finetune Qwen2.5-7B comparator vs o1 zero-shotprivacy comparator · consensus>=0.8accuracy %: 90% -> 89%No clear effect
predict actions directly with LLM instead of comparator-guided searchLLM predictors · prediction vs oracleoversharingHurt
prefer ABSTRACT over REDACT in direct predictionLLM predictors · everyday promptsprivacy protectionHurt

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