SOTAVerified

Open-Domain Question Answering

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

Papers

Showing 401–450 of 494 papers

TitleStatusHype
In Situ Answer Sentence Selection at Web-scale—0
Internet-augmented language models through few-shot prompting for open-domain question answering—0
Invar-RAG: Invariant LLM-aligned Retrieval for Better Generation—0
Investigating Information Inconsistency in Multilingual Open-Domain Question Answering—0
Is Retriever Merely an Approximator of Reader?—0
Is Table Retrieval a Solved Problem? Exploring Join-Aware Multi-Table Retrieval—0
JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking—0
KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering—0
KGI: An Integrated Framework for Knowledge Intensive Language Tasks—0
Knowledge-Aided Open-Domain Question Answering—0
Knowledge-Aware Iterative Retrieval for Multi-Agent Systems—0
Knowledge Fusion and Semantic Knowledge Ranking for Open Domain Question Answering—0
Language Models as Fact Checkers?—0
Large Language Models Can Self-Correct with Key Condition Verification—0
Lean Question Answering over Freebase from Scratch—0
Learning from Limited Labels for Long Legal Dialogue—0
Learning to answer questions—0
Learning to Answer Questions from Wikipedia Infoboxes—0
Learning to Organize Knowledge and Answer Questions with N-Gram Machines—0
Leveraging Term Banks for Answering Complex Questions: A Case for Sparse Vectors—0
LoRE: Logit-Ranked Retriever Ensemble for Enhancing Open-Domain Question Answering—0
Low-Resource Dense Retrieval for Open-Domain Question Answering: A Comprehensive Survey—0
MAUPQA: Massive Automatically-created Polish Question Answering Dataset—0
MIX : a Multi-task Learning Approach to Solve Open-Domain Question Answering—0
Modeling Context in Answer Sentence Selection Systems on a Latency Budget—0
Multifaceted Improvements for Conversational Open-Domain Question Answering—0
Multi-Granular Sequence Encoding via Dilated Compositional Units for Reading Comprehension—0
Multi-Hop Open-Domain Question Answering over Structured and Unstructured Knowledge—0
Multilingual Retrieval-Augmented Generation for Knowledge-Intensive Task—0
Multimodal Dialogue State Tracking By QA Approach with Data Augmentation—0
Multi-Paragraph Reasoning with Knowledge-enhanced Graph Neural Network—0
Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering—0
Multi-Task Retrieval-Augmented Text Generation with Relevance Sampling—0
Multi-task Retrieval for Knowledge-Intensive Tasks—0
Narrowing the Knowledge Evaluation Gap: Open-Domain Question Answering with Multi-Granularity Answers—0
Natural Language Generation at Scale: A Case Study for Open Domain Question Answering—0
Natural Language Processing in Watson—0
Neural Passage Retrieval with Improved Negative Contrast—0
Neural Retriever and Go Beyond: A Thesis Proposal—0
NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned—0
On metric embedding for boosting semantic similarity computations—0
On the Importance of Adaptive Data Collection for Extremely Imbalanced Pairwise Tasks—0
Open-domain Factoid Question Answering via Knowledge Graph Search—0
Open-Domain Question Answering—0
Open Domain Question Answering based on Text Enhanced Knowledge Graph with Hyperedge Infusion—0
Open Domain Question Answering over Tables via Dense Retrieval—0
Open Domain Question Answering over Virtual Documents: A Unified Approach for Data and Text—0
Open Domain Question Answering Using Web Tables—0
Open Domain Question Answering with Conflicting Contexts—0
Open-Domain Question Answering with Pre-Constructed Question Spaces—0
Show:102550
← PrevPage 9 of 10Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1somebodyKILT-RL2.62—Unverified
2WikipediaKILT-RL2.46—Unverified
3arxiv.org/abs/2103.06332KILT-RL2.36—Unverified
4BART + DPRKILT-RL1.9—Unverified
5RAGKILT-RL1.69—Unverified
6Training Set Retrieval (top 1)KILT-RL0—Unverified
7T5-baseKILT-RL0—Unverified
8Input CopyingKILT-RL0—Unverified
9SphereKILT-RL0—Unverified
10Random Training Set AnswerKILT-RL0—Unverified
#ModelMetricClaimedVerifiedStatus
1Re2GKILT-EM43.56—Unverified
2intersectKILT-EM38.78—Unverified
3KGI_0KILT-EM36.36—Unverified
4WikipediaKILT-EM35.32—Unverified
5RAGKILT-EM32.69—Unverified
6BERT + DPRKILT-EM31.99—Unverified
7BART + DPRKILT-EM30.06—Unverified
8Multitask DPR + BARTKILT-EM29.09—Unverified
9Multi-task DPRKILT-EM0—Unverified
10SphereKILT-EM0—Unverified
#ModelMetricClaimedVerifiedStatus
1Re2GKILT-EM57.91—Unverified
2intersectKILT-EM50.56—Unverified
3WikipediaKILT-EM45.55—Unverified
4KGI_0KILT-EM42.85—Unverified
5Multitask DPR + BARTKILT-EM42.36—Unverified
6RAGKILT-EM38.13—Unverified
7BERT + DPRKILT-EM34.48—Unverified
8BART + DPRKILT-EM31.4—Unverified
9TABiKILT-EM0—Unverified
10T5-baseKILT-EM0—Unverified
#ModelMetricClaimedVerifiedStatus
1intersectKILT-EM18.06—Unverified
2WikipediaKILT-EM11.71—Unverified
3Multitask DPR + BARTKILT-EM9.53—Unverified
4RAGKILT-EM3.21—Unverified
5BART + DPRKILT-EM1.96—Unverified
6BERT + DPRKILT-EM0.74—Unverified
7SphereKILT-EM0—Unverified
8Multi-task DPRKILT-EM0—Unverified
9GENREKILT-EM0—Unverified
10chriskueiKILT-EM0—Unverified
#ModelMetricClaimedVerifiedStatus
1SpanBERTF184.8—Unverified
2Cluster-Former (#C=512)EM68—Unverified
3Locality-Sensitive HashingEM66—Unverified
4Multi-passage BERTEM65.1—Unverified
5Sparse AttentionEM64.7—Unverified
6DECAPROPEM62.2—Unverified
7Bi-Attention + DCU-LSTMN-gram F159.5—Unverified
8Denoising QAEM58.8—Unverified
9DecaPropEM56.8—Unverified
10AMANDAN-gram F156.6—Unverified
#ModelMetricClaimedVerifiedStatus
1Fourier TransformerRouge-L26.9—Unverified
2QGRouge-L26.4—Unverified
3BARTRouge-L24.3—Unverified
4E-MCARouge-L24—Unverified
5Transformer Multitask + LayerDropRouge-L23.4—Unverified
6Multi-InrerleaveRouge-L14.63—Unverified
#ModelMetricClaimedVerifiedStatus
1Evidence Aggregation via R^3 Re-RankingEM (Quasar-T)42.3—Unverified
2Denoising QAEM (Quasar-T)42.2—Unverified
3DecaPropEM (Quasar-T)38.6—Unverified
4R^3EM (Quasar-T)35.3—Unverified
5GAEM (Quasar-T)26.4—Unverified
6BiDAFEM (Quasar-T)25.9—Unverified
#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
#ModelMetricClaimedVerifiedStatus
1SPARTAEM59.3—Unverified
2Blended RAGEM57.63—Unverified
3BERTseriniEM50.2—Unverified
4BERTseriniEM38.6—Unverified
#ModelMetricClaimedVerifiedStatus
1UniK-QAExact Match57.7—Unverified
2FiE+PAQExact Match56.3—Unverified
3FiEExact Match52.4—Unverified
4EMDR2Exact Match48.7—Unverified
#ModelMetricClaimedVerifiedStatus
1DrQAEM70—Unverified
2DCNEM66.2—Unverified
3MPCMEM65.5—Unverified
#ModelMetricClaimedVerifiedStatus
1ERNIE 2.0 LargeEM64.2—Unverified
2ERNIE 2.0 BaseEM61.3—Unverified
#ModelMetricClaimedVerifiedStatus
1UniK-QAExact Match65.5—Unverified
2BPR (linear scan; l=1000)Exact Match56.8—Unverified
#ModelMetricClaimedVerifiedStatus
1EMDR2Exact Match52.5—Unverified
#ModelMetricClaimedVerifiedStatus
1UnitedQA (Hybrid)Exact Match70.5—Unverified