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 51–100 of 268 papers

TitleStatusHype
Densifying Sparse Representations for Passage Retrieval by Representational SlicingCode1
Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?Code1
MFAQ: a Multilingual FAQ DatasetCode1
Simple Entity-Centric Questions Challenge Dense RetrieversCode1
Phrase Retrieval Learns Passage Retrieval, TooCode1
R2-D2: A Modular Baseline for Open-Domain Question AnsweringCode1
Robust Retrieval Augmented Generation for Zero-shot Slot FillingCode1
Dealing with Typos for BERT-based Passage Retrieval and RankingCode1
On Single and Multiple Representations in Dense Passage RetrievalCode1
Unsupervised Corpus Aware Language Model Pre-training for Dense Passage RetrievalCode1
One Question Answering Model for Many Languages with Cross-lingual Dense Passage RetrievalCode1
Exemplars-guided Empathetic Response Generation Controlled by the Elements of Human CommunicationCode1
Efficient Passage Retrieval with Hashing for Open-domain Question AnsweringCode1
Corpus-Level Evaluation for Event QA: The IndiaPoliceEvents Corpus Covering the 2002 Gujarat ViolenceCode1
Passage Retrieval for Outside-Knowledge Visual Question AnsweringCode1
Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage RetrievalCode1
Overview of the TREC 2020 deep learning trackCode1
Weakly Supervised Label SmoothingCode1
Structural Text Segmentation of Legal DocumentsCode1
Learning To Retrieve: How to Train a Dense Retrieval Model Effectively and EfficientlyCode1
CoRT: Complementary Rankings from TransformersCode1
Open-Domain Question Answering Goes Conversational via Question RewritingCode1
Embedding-based Zero-shot Retrieval through Query GenerationCode1
Generation-Augmented Retrieval for Open-domain Question AnsweringCode1
Leveraging Passage Retrieval with Generative Models for Open Domain Question AnsweringCode1
Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text RetrievalCode1
Query Resolution for Conversational Search with Limited SupervisionCode1
Dense Passage Retrieval for Open-Domain Question AnsweringCode1
Overview of the TREC 2019 deep learning trackCode1
Passage Re-ranking with BERTCode1
GenKI: Enhancing Open-Domain Question Answering with Knowledge Integration and Controllable Generation in Large Language ModelsCode0
Batched Self-Consistency Improves LLM Relevance Assessment and Ranking—0
Dense Passage Retrieval in Conversational SearchCode0
Pseudo-Relevance Feedback Can Improve Zero-Shot LLM-Based Dense Retrieval—0
TempRetriever: Fusion-based Temporal Dense Passage Retrieval for Time-Sensitive Questions—0
From Retrieval to Generation: Comparing Different Approaches—0
Say Less, Mean More: Leveraging Pragmatics in Retrieval-Augmented Generation—0
Multi-stage Training of Bilingual Islamic LLM for Neural Passage Retrieval—0
Passage Segmentation of Documents for Extractive Question Answering—0
Multilingual Open QA on the MIA Shared Task—0
Query pipeline optimization for cancer patient question answering systems—0
Optimized Quran Passage Retrieval Using an Expanded QA Dataset and Fine-Tuned Language Models—0
Towards Brain Passage Retrieval -- An Investigation of EEG Query Representations—0
Time-Reversal Provides Unsupervised Feedback to LLMs—0
DynRank: Improving Passage Retrieval with Dynamic Zero-Shot Prompting Based on Question Classification—0
Mind the Gap: A Generalized Approach for Cross-Modal Embedding Alignment—0
Deep Learning Based Dense Retrieval: A Comparative Study—0
Improve Dense Passage Retrieval with Entailment Tuning—0
Passage Retrieval of Polish Texts Using OKAPI BM25 and an Ensemble of Cross EncodersCode0
Learning When to Retrieve, What to Rewrite, and How to Respond in Conversational QA—0
Show:102550
← PrevPage 2 of 6Next →

No leaderboard results yet.