SOTAVerified

Natural Questions

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 178 papers

TitleStatusHype
Quick Dense Retrievers Consume KALE: Post Training Kullback Leibler Alignment of Embeddings for Asymmetrical dual encoders—0
Uncovering Challenges of Solving the Continuous Gromov-Wasserstein ProblemCode0
Zero-shot Clarifying Question Generation for Conversational Search—0
Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL RobustnessCode1
DSI++: Updating Transformer Memory with New Documents—0
Momentum Contrastive Pre-training for Question Answering—0
On the Effectiveness of Parameter-Efficient Fine-TuningCode1
DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question AnsweringCode1
Closed-book Question Generation via Contrastive LearningCode0
Improving Question Answering with Generation of NQ-like Questions—0
Recitation-Augmented Language ModelsCode1
LFKQG: A Controlled Generation Framework with Local Fine-tuning for Question Generation over Knowledge Bases—0
PROD: Progressive Distillation for Dense RetrievalCode0
Promptagator: Few-shot Dense Retrieval From 8 Examples—0
DPTDR: Deep Prompt Tuning for Dense Passage RetrievalCode0
Atlas: Few-shot Learning with Retrieval Augmented Language ModelsCode2
Masked Autoencoders As The Unified Learners For Pre-Trained Sentence Representation—0
MultiSpanQA: A Dataset for Multi-Span Question AnsweringCode1
Natural Questions in Icelandic—0
Unfooling Perturbation-Based Post Hoc ExplainersCode0
QAMPARI: An Open-domain Question Answering Benchmark for Questions with Many Answers from Multiple ParagraphsCode2
Would You Ask it that Way? Measuring and Improving Question Naturalness for Knowledge Graph Question AnsweringCode1
Table Retrieval May Not Necessitate Table-specific Model DesignCode1
A Copy-Augmented Generative Model for Open-Domain Question Answering—0
GNN-encoder: Learning a Dual-encoder Architecture via Graph Neural Networks for Dense Passage Retrieval—0
How Do We Answer Complex Questions: Discourse Structure of Long-form AnswersCode1
Teaching language models to support answers with verified quotes—0
Asyncval: A Toolkit for Asynchronously Validating Dense Retriever Checkpoints during TrainingCode1
ST-MoE: Designing Stable and Transferable Sparse Expert ModelsCode3
Text and Code Embeddings by Contrastive Pre-TrainingCode1
CQMrobust: A Chinese Dataset of Linguistically Perturbed Natural Questions for Evaluating the Robustness of Question Matching Models—0
Table Retrieval Does Not Necessitate Table-specific Model Design—0
Zero-shot Commonsense Question Answering with Cloze Translation and Consistency OptimizationCode0
Continual Learning with Knowledge Transfer for Sentiment ClassificationCode1
DuQM: A Chinese Dataset of Linguistically Perturbed Natural Questions for Evaluating the Robustness of Question Matching ModelsCode0
You Only Need One Model for Open-domain Question Answering—0
TempoQR: Temporal Question Reasoning over Knowledge GraphsCode1
Scaling Language Models: Methods, Analysis & Insights from Training GopherCode2
Zero-Shot Open-Book Question AnsweringCode0
How do we answer complex questions: Discourse structure of long form answers—0
Open Domain Question Answering over Virtual Documents: A Unified Approach for Data and Text—0
Question Answering for Complex Electronic Health Records Database using Unified Encoder-Decoder Architecture—0
ConQuest: Contextual Question Paraphrasing through Answer-Aware Synthetic Question Generation—0
What’s in a Name? Answer Equivalence For Open-Domain Question AnsweringCode0
Challenges in Generalization in Open Domain Question Answering—0
A Copy-Augmented Generative Model for Open-Domain Question Answering—0
Open Domain Question Answering with A Unified Knowledge InterfaceCode1
Sharpness-Aware Minimization Improves Language Model Generalization—0
RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-rankingCode0
Adversarial Retriever-Ranker for dense text retrievalCode0
Show:102550
← PrevPage 2 of 4Next →

No leaderboard results yet.