AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Pisces: Cryptography-based Private Retrieval-Augmented Generation with Dual-Path Retrieval

Xiaojian Liang, Lushan Song, Shishuai Du, Weicheng Zhu, Tan Li Hui Faith, Jun Jie Sim, Haibing Jin, Zhenghao Wu, Yingting Liu, Xin Zhang, Jiang-Ming Yang, Pu Duan

ICLR 2026 · Large language models › Retrieval and knowledge · approach: RAG robustness and evaluation

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
add coarse-to-fine strategy (SimHash coarse matching) to encrypted semantic retrieval (ablation)Pisces semantic path · large datasets (HotpotQA)retrieval time: saves 38.78% ~ 41.21% timeImproved
add coarse-to-fine strategy to encrypted semantic retrieval (ablation)Pisces semantic path · large datasetsupload overhead: reduces by 67.53% ~ 67.78%Improved
add coarse-to-fine strategy to encrypted semantic retrieval (ablation)Pisces semantic path · large datasetsdownload overhead: reduces by 68.49% ~ 68.77%Improved
add coarse-to-fine strategy to encrypted semantic retrieval (ablation)Pisces semantic path · ClapNQ Dev answerable (small)retrieval time: 1.855 -> 3.56Hurt
add coarse-to-fine strategy to encrypted semantic retrieval (ablation)Pisces semantic path · ClapNQ Dev answerableretrieval accuracy: 100.00% -> 86.83%Hurt
use multi-instance labeled PSI instead of labeled PSI (LSE) (ablation)Pisces lexical path · HotpotQA Dev distractorrunning time (s): 1051.98 -> 2.35Improved
use multi-instance labeled PSI instead of labeled PSI (LSE) (ablation)Pisces lexical path · HotpotQA Dev distractorupload (MB): 161.61 -> 0.0006Improved
use multi-instance labeled PSI instead of labeled PSI (LSE) (ablation)Pisces lexical path · HotpotQA Dev distractordownload (MB): 382.26 -> 79.82Improved
combine lexical with semantic retrieval (dual path) instead of semantic only (ablation)Pisces · ClapNQ Dev answerableTop-5 accuracy vs ground truth: 30.14% -> 58.05%Improved
use Pisces instead of DP-RAG (eps=1)RAG retrieval · ClapNQ Dev answerableTop-5 accuracy vs ground truth: 26.37% -> 58.05%Improved
use Pisces instead of RemoteRAG (eps=1280)RAG retrieval · ClapNQ Dev answerableTop-5 accuracy vs ground truth: 35.54% -> 58.05%Improved
use Pisces instead of plaintext retrievalRAG retrieval · ClapNQ Dev answerableTop-5 accuracy vs ground truth: 59.66% -> 58.05%Mixed

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