AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Improving the Accuracy of Dense Retrieval on the Quantized Indexes via Gradient Optimization of the Target Embeddings

Cong Tan, Yongqi Shao, Hong Huo, Tao Fang

AAAI 2026 · Architectures and efficiency › RNNs and normalization · approach: Dataset condensation and flow estimation · 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
train with gradient-updated cached target embeddings and similarity-based large negativesANCE model · MS MARCO Dev (QHNSW index)MRR@10: 12.74 -> 26.32Improved
same trainingANCE model · MS MARCO Dev (FlatIP index)MRR@10: 32.26 -> 29.71Hurt
same trainingANCE model · TriviaQA Test (QHNSW index)R@1: 51.22 -> 53.91Improved
same trainingANCE model · TriviaQA Test (QHNSW index)R@10: 74.80 -> 74.39Hurt
same trainingDPR model · Natural Questions Test (QHNSW index)R@1: 46.06 -> 51.52Improved
same trainingDPR model · Natural Questions Test (FlatIP index)R@1: 52.13 -> 52.49No clear effect
add similarity-based large negatives retrieved from the quantized index (ablation)DPR on QHNSW · Natural Questions TestR@1: 46.06 -> 49.72Improved
add similarity-based large negatives retrieved from the quantized index (ablation)DPR on QHNSW · Natural Questions TestR@100: 84.65 -> 84.12Hurt
add gradient updates of cached target embeddings on top of large negatives (ablation)DPR on QHNSW · Natural Questions TestR@1: 49.72 -> 51.52Improved
set temperature to 8 versus other values from 0.5 to 16 (ablation)training · Natural Questions Test (QHNSW)R@1: 49.2 -> 51.5Improved

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