SOTAVerified

Natural Questions

Papers

Showing 150 of 178 papers

TitleStatusHype
LayerSkip: Enabling Early Exit Inference and Self-Speculative DecodingCode3
GNN-RAG: Graph Neural Retrieval for Large Language Model ReasoningCode3
ST-MoE: Designing Stable and Transferable Sparse Expert ModelsCode3
Scaling Language Models: Methods, Analysis & Insights from Training GopherCode2
Relevance-guided Supervision for OpenQA with ColBERTCode2
JADE: A Linguistics-based Safety Evaluation Platform for Large Language ModelsCode2
QAMPARI: An Open-domain Question Answering Benchmark for Questions with Many Answers from Multiple ParagraphsCode2
Atlas: Few-shot Learning with Retrieval Augmented Language ModelsCode2
DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-SolvingCode2
Text and Code Embeddings by Contrastive Pre-TrainingCode1
CLAPNQ: Cohesive Long-form Answers from Passages in Natural Questions for RAG systemsCode1
RECONSIDER: Re-Ranking using Span-Focused Cross-Attention for Open Domain Question AnsweringCode1
TempoQR: Temporal Question Reasoning over Knowledge GraphsCode1
Generative Retrieval via Term Set GenerationCode1
Table Retrieval May Not Necessitate Table-specific Model DesignCode1
Would You Ask it that Way? Measuring and Improving Question Naturalness for Knowledge Graph Question AnsweringCode1
MultiSpanQA: A Dataset for Multi-Span Question AnsweringCode1
MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question AnsweringCode1
Lightweight and Direct Document Relevance Optimization for Generative Information RetrievalCode1
Model-enhanced Vector IndexCode1
Multi-Granularity Guided Fusion-in-DecoderCode1
Poisoning Retrieval Corpora by Injecting Adversarial PassagesCode1
Event Extraction by Answering (Almost) Natural QuestionsCode1
Recitation-Augmented Language ModelsCode1
QED: A Framework and Dataset for Explanations in Question AnsweringCode1
C3VQG: Category Consistent Cyclic Visual Question GenerationCode1
Asyncval: A Toolkit for Asynchronously Validating Dense Retriever Checkpoints during TrainingCode1
Exploiting Abstract Meaning Representation for Open-Domain Question AnsweringCode1
Constructing and Evaluating Declarative RAG Pipelines in PyTerrierCode1
Continual Learning with Knowledge Transfer for Sentiment ClassificationCode1
Efficient Passage Retrieval with Hashing for Open-domain Question AnsweringCode1
Knowledge Guided Text Retrieval and Reading for Open Domain Question AnsweringCode1
Generation-Augmented Retrieval for Open-domain Question AnsweringCode1
AutoQA: From Databases To QA Semantic Parsers With Only Synthetic Training DataCode1
Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage RetrievalCode1
Corpus-Level Evaluation for Event QA: The IndiaPoliceEvents Corpus Covering the 2002 Gujarat ViolenceCode1
End-to-End Training of Neural Retrievers for Open-Domain Question AnsweringCode1
RealFormer: Transformer Likes Residual AttentionCode1
Leveraging Passage Retrieval with Generative Models for Open Domain Question AnsweringCode1
How Do We Answer Complex Questions: Discourse Structure of Long-form AnswersCode1
LLaSA: A Multimodal LLM for Human Activity Analysis Through Wearable and Smartphone SensorsCode1
DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question AnsweringCode1
Rider: Reader-Guided Passage Reranking for Open-Domain Question AnsweringCode1
Document Modeling with Graph Attention Networks for Multi-grained Machine Reading ComprehensionCode1
On the Effectiveness of Parameter-Efficient Fine-TuningCode1
Open Domain Question Answering with A Unified Knowledge InterfaceCode1
Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL RobustnessCode1
AdANNS: A Framework for Adaptive Semantic SearchCode1
FastFiD: Improve Inference Efficiency of Open Domain Question Answering via Sentence SelectionCode1
ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks0
Show:102550
← PrevPage 1 of 4Next →

No leaderboard results yet.