SOTAVerified

Passage Retrieval

Passage retrieval is a specialized type of IR application that retrieves relevant passages (or pieces of text) rather than an entire ranked set of documents.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 268 papers

TitleStatusHype
BM25S: Orders of magnitude faster lexical search via eager sparse scoringCode5
CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation GenerationCode2
Never Lost in the Middle: Mastering Long-Context Question Answering with Position-Agnostic Decompositional TrainingCode2
Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question AnsweringCode2
MiniLLM: Knowledge Distillation of Large Language ModelsCode2
Retrieval Oriented Masking Pre-training Language Model for Dense Passage RetrievalCode2
Retrieval Augmented Visual Question Answering with Outside KnowledgeCode2
QAMPARI: An Open-domain Question Answering Benchmark for Questions with Many Answers from Multiple ParagraphsCode2
Multi-CPR: A Multi Domain Chinese Dataset for Passage RetrievalCode2
SGPT: GPT Sentence Embeddings for Semantic SearchCode2
ColBERTv2: Effective and Efficient Retrieval via Lightweight Late InteractionCode2
BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval ModelsCode2
Optimized Text Embedding Models and Benchmarks for Amharic Passage RetrievalCode1
GuRE:Generative Query REwriter for Legal Passage RetrievalCode1
PeerQA: A Scientific Question Answering Dataset from Peer ReviewsCode1
FastFiD: Improve Inference Efficiency of Open Domain Question Answering via Sentence SelectionCode1
ArabicaQA: A Comprehensive Dataset for Arabic Question AnsweringCode1
Drop your Decoder: Pre-training with Bag-of-Word Prediction for Dense Passage RetrievalCode1
RecJPQ: Training Large-Catalogue Sequential RecommendersCode1
LePaRD: A Large-Scale Dataset of Judges Citing PrecedentsCode1
Fine-Tuning LLaMA for Multi-Stage Text RetrievalCode1
CSPRD: A Financial Policy Retrieval Dataset for Chinese Stock MarketCode1
End-to-End Query Term WeightingCode1
Query Encoder Distillation via Embedding Alignment is a Strong Baseline Method to Boost Dense Retriever Online EfficiencyCode1
I^3 Retriever: Incorporating Implicit Interaction in Pre-trained Language Models for Passage RetrievalCode1
Show:102550
← PrevPage 1 of 11Next →

No leaderboard results yet.