AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Privacy Preserving In-Context-Learning Framework for Large Language Models

Bishnu Bhusal, Manoj Acharya, Ramneet Kaur, Colin Samplawski, Anirban Roy, Adam D. Cobb, Rohit Chadha, Susmit Jha

AAAI 2026 · Federated learning and privacy › Differential privacy · approach: Differentially private synthetic data · 1 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
use proposed clip-average-blend DP aggregation instead of Amin et al. 2024private synthetic ICL demos · TREC 4-shot ICL (eps=1)accuracy (%): 39.2 -> 63.0Improved
use proposed aggregation instead of Amin et al. 2024private synthetic ICL demos · AGNews 4-shot ICL (eps=inf)accuracy (%): 76.8 -> 73.5Hurt
use proposed aggregation instead of Amin et al. 2024private synthetic ICL demos · MIT-D 4-shot ICL (eps=1)accuracy (%): 84.5 -> 79.9Hurt
use proposed aggregation instead of Amin et al. 2024private synthetic ICL demos · DBPedia 4-shot ICL (eps=1)accuracy (%): 75.1 -> 76.8No clear effect
blend private logits with public-prompt logitsprivate synthetic ICL demos · several ICL tasksaccuracy (%)Improved
increase privacy budget eps (1 to inf) (ablation)private synthetic ICL demos · DBPedia ICL (4-shot)accuracy (%): 76.80 -> 80.94Improved
increase privacy budget eps (1 to inf) on TREC (ablation)private synthetic ICL demos · TREC ICL (1-shot)accuracy (%): 68.32 -> 62.40Hurt
increase LLM size/quality (Llama-3.2-1B to 8B) (ablation)private synthetic ICL demos · DBPedia ICL (eps=1, model sweep)accuracy (%): 53.9 -> 89.9Improved
use DP synthetic demonstrations instead of real private samplesprivate synthetic ICL demos · Enron membership inferenceMIA AUC: 94.20 -> 51.78Improved
use proposed aggregation instead of Amin et al. 2024 for JSONprivate synthetic generation · WikiMoviesJSON (eps=1)validates (%): 74.2 -> 81.1Improved

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