SOTAVerified

Open-Domain Question Answering

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

Papers

Showing 101110 of 494 papers

TitleStatusHype
Conformal Language ModelingCode1
Context Awareness Gate For Retrieval Augmented GenerationCode1
Latent Retrieval for Weakly Supervised Open Domain Question AnsweringCode1
MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question AnsweringCode1
Multi-Granularity Guided Fusion-in-DecoderCode1
Narrative Question Answering with Cutting-Edge Open-Domain QA Techniques: A Comprehensive StudyCode1
Contextualized Sparse Representations for Real-Time Open-Domain Question AnsweringCode1
On the Risk of Misinformation Pollution with Large Language ModelsCode1
Autoregressive Entity RetrievalCode1
Densely Connected Attention Propagation for Reading ComprehensionCode1
Show:102550
← PrevPage 11 of 50Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1somebodyKILT-RL2.62Unverified
2WikipediaKILT-RL2.46Unverified
3arxiv.org/abs/2103.06332KILT-RL2.36Unverified
4BART + DPRKILT-RL1.9Unverified
5RAGKILT-RL1.69Unverified
6T5-baseKILT-RL0Unverified
7GENREKILT-RL0Unverified
8Multi-task DPRKILT-RL0Unverified
9BARTKILT-RL0Unverified
10Training Set Retrieval (top 1)KILT-RL0Unverified
#ModelMetricClaimedVerifiedStatus
1Re2GKILT-EM43.56Unverified
2intersectKILT-EM38.78Unverified
3KGI_0KILT-EM36.36Unverified
4WikipediaKILT-EM35.32Unverified
5RAGKILT-EM32.69Unverified
6BERT + DPRKILT-EM31.99Unverified
7BART + DPRKILT-EM30.06Unverified
8Multitask DPR + BARTKILT-EM29.09Unverified
9SphereKILT-EM0Unverified
10T5-baseKILT-EM0Unverified
#ModelMetricClaimedVerifiedStatus
1Re2GKILT-EM57.91Unverified
2intersectKILT-EM50.56Unverified
3WikipediaKILT-EM45.55Unverified
4KGI_0KILT-EM42.85Unverified
5Multitask DPR + BARTKILT-EM42.36Unverified
6RAGKILT-EM38.13Unverified
7BERT + DPRKILT-EM34.48Unverified
8BART + DPRKILT-EM31.4Unverified
9Multi-task DPRKILT-EM0Unverified
10SphereKILT-EM0Unverified
#ModelMetricClaimedVerifiedStatus
1intersectKILT-EM18.06Unverified
2WikipediaKILT-EM11.71Unverified
3Multitask DPR + BARTKILT-EM9.53Unverified
4RAGKILT-EM3.21Unverified
5BART + DPRKILT-EM1.96Unverified
6BERT + DPRKILT-EM0.74Unverified
7SphereKILT-EM0Unverified
8Multi-task DPRKILT-EM0Unverified
9GENREKILT-EM0Unverified
10chriskueiKILT-EM0Unverified
#ModelMetricClaimedVerifiedStatus
1SpanBERTF184.8Unverified
2Cluster-Former (#C=512)EM68Unverified
3Locality-Sensitive HashingEM66Unverified
4Multi-passage BERTEM65.1Unverified
5Sparse AttentionEM64.7Unverified
6DECAPROPEM62.2Unverified
7Bi-Attention + DCU-LSTMN-gram F159.5Unverified
8Denoising QAEM58.8Unverified
9DecaPropEM56.8Unverified
10AMANDAN-gram F156.6Unverified
#ModelMetricClaimedVerifiedStatus
1Fourier TransformerRouge-L26.9Unverified
2QGRouge-L26.4Unverified
3BARTRouge-L24.3Unverified
4E-MCARouge-L24Unverified
5Transformer Multitask + LayerDropRouge-L23.4Unverified
6Multi-InrerleaveRouge-L14.63Unverified
#ModelMetricClaimedVerifiedStatus
1Evidence Aggregation via R^3 Re-RankingEM (Quasar-T)42.3Unverified
2Denoising QAEM (Quasar-T)42.2Unverified
3DecaPropEM (Quasar-T)38.6Unverified
4R^3EM (Quasar-T)35.3Unverified
5GAEM (Quasar-T)26.4Unverified
6BiDAFEM (Quasar-T)25.9Unverified
#ModelMetricClaimedVerifiedStatus
1FiEExact Match58.4Unverified
2R2-D2 HN-DPRExact Match55.9Unverified
3UniK-QAExact Match54.9Unverified
4UnitedQA (Hybrid)Exact Match54.7Unverified
5BPR (linear scan; l=1000)Exact Match41.6Unverified
#ModelMetricClaimedVerifiedStatus
1SPARTAEM59.3Unverified
2Blended RAGEM57.63Unverified
3BERTseriniEM50.2Unverified
4BERTseriniEM38.6Unverified
#ModelMetricClaimedVerifiedStatus
1UniK-QAExact Match57.7Unverified
2FiE+PAQExact Match56.3Unverified
3FiEExact Match52.4Unverified
4EMDR2Exact Match48.7Unverified
#ModelMetricClaimedVerifiedStatus
1DrQAEM70Unverified
2DCNEM66.2Unverified
3MPCMEM65.5Unverified
#ModelMetricClaimedVerifiedStatus
1ERNIE 2.0 LargeEM64.2Unverified
2ERNIE 2.0 BaseEM61.3Unverified
#ModelMetricClaimedVerifiedStatus
1UniK-QAExact Match65.5Unverified
2BPR (linear scan; l=1000)Exact Match56.8Unverified
#ModelMetricClaimedVerifiedStatus
1EMDR2Exact Match52.5Unverified
#ModelMetricClaimedVerifiedStatus
1UnitedQA (Hybrid)Exact Match70.5Unverified