SOTAVerified

Natural Questions

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 178 papers

TitleStatusHype
Constructing and Evaluating Declarative RAG Pipelines in PyTerrierCode1
Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds—0
CRAFT: Training-Free Cascaded Retrieval for Tabular QA—0
PoisonArena: Uncovering Competing Poisoning Attacks in Retrieval-Augmented GenerationCode0
Pre-training vs. Fine-tuning: A Reproducibility Study on Dense Retrieval Knowledge AcquisitionCode0
GRADA: Graph-based Reranker against Adversarial Documents AttackCode0
Chain-of-Defensive-Thought: Structured Reasoning Elicits Robustness in Large Language Models against Reference Corruption—0
S1-Bench: A Simple Benchmark for Evaluating System 1 Thinking Capability of Large Reasoning ModelsCode0
Lightweight and Direct Document Relevance Optimization for Generative Information RetrievalCode1
Towards Fully Exploiting LLM Internal States to Enhance Knowledge Boundary Perception—0
CacheFocus: Dynamic Cache Re-Positioning for Efficient Retrieval-Augmented Generation—0
Optimizing Knowledge Integration in Retrieval-Augmented Generation with Self-Selection—0
DragonVerseQA: Open-Domain Long-Form Context-Aware Question-AnsweringCode0
Advanced RAG Models with Graph Structures: Optimizing Complex Knowledge Reasoning and Text Generation—0
ELOQ: Resources for Enhancing LLM Detection of Out-of-Scope QuestionsCode0
Local Explanations and Self-Explanations for Assessing Faithfulness in black-box LLMs—0
Investigating Context-Faithfulness in Large Language Models: The Roles of Memory Strength and Evidence Style—0
FastFiD: Improve Inference Efficiency of Open Domain Question Answering via Sentence SelectionCode1
AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation—0
LLaSA: A Multimodal LLM for Human Activity Analysis Through Wearable and Smartphone SensorsCode1
DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-SolvingCode2
Unifying Multimodal Retrieval via Document Screenshot Embedding—0
Scaling the Vocabulary of Non-autoregressive Models for Efficient Generative Retrieval—0
RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented GenerationCode0
GNN-RAG: Graph Neural Retrieval for Large Language Model ReasoningCode3
DGRC: An Effective Fine-tuning Framework for Distractor Generation in Chinese Multi-choice Reading Comprehension—0
LayerSkip: Enabling Early Exit Inference and Self-Speculative DecodingCode3
KazQAD: Kazakh Open-Domain Question Answering DatasetCode0
Multi-Granularity Guided Fusion-in-DecoderCode1
CLAPNQ: Cohesive Long-form Answers from Passages in Natural Questions for RAG systemsCode1
Pre-training Cross-lingual Open Domain Question Answering with Large-scale Synthetic SupervisionCode0
Summarization-Based Document IDs for Generative Retrieval with Language ModelsCode0
JADE: A Linguistics-based Safety Evaluation Platform for Large Language ModelsCode2
Poisoning Retrieval Corpora by Injecting Adversarial PassagesCode1
ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks—0
Retrieval meets Long Context Large Language Models—0
Model-enhanced Vector IndexCode1
Diversifying Question Generation over Knowledge Base via External Natural Questions—0
On Monotonic Aggregation for Open-domain QACode0
TRAQ: Trustworthy Retrieval Augmented Question Answering via Conformal PredictionCode0
When to Read Documents or QA History: On Unified and Selective Open-domain QA—0
AdANNS: A Framework for Adaptive Semantic SearchCode1
Information Association for Language Model Updating by Mitigating LM-Logical Discrepancy—0
Exploiting Abstract Meaning Representation for Open-Domain Question AnsweringCode1
RFiD: Towards Rational Fusion-in-Decoder for Open-Domain Question AnsweringCode0
Generative Retrieval via Term Set GenerationCode1
CRITIC: Large Language Models Can Self-Correct with Tool-Interactive CritiquingCode0
TOME: A Two-stage Approach for Model-based Retrieval—0
MeeQA: Natural Questions in Meeting TranscriptsCode0
Noise-Robust Dense Retrieval via Contrastive Alignment Post Training—0
Show:102550
← PrevPage 1 of 4Next →

No leaderboard results yet.