SOTAVerified

Passage Re-Ranking

Passage re-ranking is the task of scoring and re-ranking a collection of retrieved documents based on an input query.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 11–20 of 32 papers

TitleStatusHype
Dealing with Typos for BERT-based Passage Retrieval and RankingCode1
Few-shot Reranking for Multi-hop QA via Language Model PromptingCode1
Exploring the Effectiveness of Multi-stage Fine-tuning for Cross-encoder Re-rankersCode0
Exploiting Sentence-Level Representations for Passage RankingCode0
RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-rankingCode0
Improving Conversational Passage Re-ranking with View EnsembleCode0
Societal Biases in Retrieved Contents: Measurement Framework and Adversarial Mitigation for BERT RankersCode0
An Updated Duet Model for Passage Re-rankingCode0
A Modern Perspective on Query Likelihood with Deep Generative Retrieval ModelsCode0
Towards Robust Passage Re-Ranking Model by Mitigating Lexical Match Bias—0
Show:102550
← PrevPage 2 of 4Next →
All datasetsMS MARCOTREC-PM

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1HLATRMRR0.42—Unverified
2BERT + Doc2queryMRR0.37—Unverified
3BERT + Small TrainingMRR0.36—Unverified
4Duet v2MRR0.25—Unverified
#ModelMetricClaimedVerifiedStatus
1BERT + Doc2querymAP36.5—Unverified