SOTAVerified

Open-Domain Question Answering

Open-domain question answering is the task of question answering on open-domain datasets such as Wikipedia.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 494 papers

TitleStatusHype
TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document ReasoningCode2
Efficient Context Selection for Long-Context QA: No Tuning, No Iteration, Just Adaptive-k—0
ECoRAG: Evidentiality-guided Compression for Long Context RAGCode1
GenKI: Enhancing Open-Domain Question Answering with Knowledge Integration and Controllable Generation in Large Language ModelsCode0
NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement LearningCode1
Single LLM, Multiple Roles: A Unified Retrieval-Augmented Generation Framework Using Role-Specific Token Optimization—0
Unveiling Knowledge Utilization Mechanisms in LLM-based Retrieval-Augmented Generation—0
Scaling Reasoning can Improve Factuality in Large Language ModelsCode0
Benchmarking LLM-based Relevance Judgment MethodsCode0
Multilingual Retrieval-Augmented Generation for Knowledge-Intensive Task—0
Show:102550
← PrevPage 1 of 50Next →
All datasetsKILT: ELI5KILT: Natural QuestionsKILT: TriviaQAKILT: HotpotQASearchQAELI5QUASARNatural QuestionsSQuAD1.1 devWebQuestionsSQuAD1.1DuReader

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1FiEExact Match58.4—Unverified
2R2-D2 HN-DPRExact Match55.9—Unverified
3UniK-QAExact Match54.9—Unverified
4UnitedQA (Hybrid)Exact Match54.7—Unverified
5BPR (linear scan; l=1000)Exact Match41.6—Unverified