AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Embedding-Based Context-Aware Reranker

Ye Yuan, Mohammad Amin Shabani, Siqi Liu

ICLR 2026 · Large language models › Retrieval and knowledge · approach: RAG robustness and evaluation · 3 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
add document ID embeddings and passage position encodings (ablation)EBCAR · ConTEB InsurancenDCG@10: 34.16 -> 40.74Improved
add document ID embeddings and passage position encodings (ablation)EBCAR · ConTEB SQuADnDCG@10: 60.87 -> 71.62Improved
add document ID embeddings and passage position encodings (ablation)EBCAR · ConTEB FootballnDCG@10: 42.88 -> 80.19Improved
add hybrid attention (shared full plus dedicated masked) (ablation)EBCAR · ConTEB SQuADnDCG@10: 47.52 -> 71.62Improved
add hybrid attention (shared full plus dedicated masked) (ablation)EBCAR · ConTEB FootballnDCG@10: 41.93 -> 80.19Improved
add hybrid attention (shared full plus dedicated masked) (ablation)EBCAR · ConTEB MLDRnDCG@10: 74.55 -> 75.26Improved
add both position info and hybrid attention (ablation)EBCAR · ConTEB FootballnDCG@10: 5.28 -> 80.19Improved
add both position info and hybrid attention (ablation)EBCAR · ConTEB InsurancenDCG@10: 2.88 -> 40.74Improved
replace Contriever with stronger E5 embeddingsEBCAR · ConTEB FootballnDCG@10: 80.19 -> 80.64Improved
replace Contriever with stronger E5 embeddingsEBCAR · ConTEB MLDRnDCG@10: 75.26 -> 77.36Improved
replace Contriever with stronger E5 embeddingsEBCAR · ConTEB ESGnDCG@10: 37.20 -> 36.88No clear effect
use updated query embedding in contrastive loss instead of fixed query embedding (ablation)EBCAR · training stabilitynDCG@10Hurt

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