Question Answering

Question answering can be segmented into domain-specific tasks like community question answering and knowledge-base question answering. Popular benchmark datasets for evaluation question answering systems include SQuAD, HotPotQA, bAbI, TriviaQA, WikiQA, and many others. Models for question answering are typically evaluated on metrics like EM and F1. Some recent top performing models are T5 and XLNet.

( Image credit: SQuAD )

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 3211–3220 of 10817 papers

Title	Date	Tasks	Status	Score
Keep Security! Benchmarking Security Policy Preservation in Large Language Model Contexts Against Indirect Attacks in Question Answering	May 21, 2025	BenchmarkingLanguage Modeling	CodeCode Available	5
An Empirical Comparison of Generative Approaches for Product Attribute-Value Identification	Jul 1, 2024	AttributeAttribute Mining	CodeCode Available	5
On the Importance of Adaptive Data Collection for Extremely Imbalanced Pairwise Tasks	Oct 10, 2020	Active LearningOpen-Domain Question Answering	CodeCode Available	5
On the Influence of Context Size and Model Choice in Retrieval-Augmented Generation Systems	Feb 20, 2025	Long Form Question AnsweringQuestion Answering	CodeCode Available	5
DBLP-QuAD: A Question Answering Dataset over the DBLP Scholarly Knowledge Graph	Mar 23, 2023	Question Answering	CodeCode Available	5
On the Summarization of Consumer Health Questions	Jul 1, 2019	Data AugmentationQuestion Answering	CodeCode Available	5
Automatic Generation of Contrast Sets from Scene Graphs: Probing the Compositional Consistency of GQA	Mar 17, 2021	Question AnsweringRelational Reasoning	CodeCode Available	5
K-COMP: Retrieval-Augmented Medical Domain Question Answering With Knowledge-Injected Compressor	Jan 23, 2025	Question AnsweringRAG	CodeCode Available	5
An empirical analysis of existing systems and datasets toward general simple question answering	Dec 1, 2020	Natural Language UnderstandingQuestion Answering	CodeCode Available	5
Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering	Jul 21, 2016	Answer GenerationQuestion Answering	CodeCode Available	5

Show:10 25 50

← PrevPage 322 of 1082Next →

All datasets SQuAD2.0 SQuAD1.1 HotpotQA PIQA BoolQ COPA TriviaQA SQuAD1.1 dev Natural Questions OpenBookQA TruthfulQA MultiRC

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	IE-Net (ensemble)	EM	90.94	—	Unverified
2	FPNet (ensemble)	EM	90.87	—	Unverified
3	IE-NetV2 (ensemble)	EM	90.86	—	Unverified
4	SA-Net on Albert (ensemble)	EM	90.72	—	Unverified
5	SA-Net-V2 (ensemble)	EM	90.68	—	Unverified
6	FPNet (ensemble)	EM	90.6	—	Unverified
7	Retro-Reader (ensemble)	EM	90.58	—	Unverified
8	EntitySpanFocusV2 (ensemble)	EM	90.52	—	Unverified
9	TransNets + SFVerifier + SFEnsembler (ensemble)	EM	90.49	—	Unverified
10	EntitySpanFocus+AT (ensemble)	EM	90.45	—	Unverified