Introduces 2WikiMultiHopQA, a multi-hop QA dataset with explicit evidence chains generated via templates and Wikidata logical rules to force and evaluate multi-hop reasoning.
ArXiv, abs/2004.07347
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
TaNOS improves cross-domain numerical reasoning over tables by combining header anonymization, operation sketches, and self-supervised pretraining, achieving 80.13% accuracy on FinQA with 10% of training data.
RELOOP unifies retrieval across text, tables, and KGs via hierarchical sequences and dual-agent guided iteration, reporting EM/F1 gains over baselines on HotpotQA, HybridQA/TAT-QA, and MetaQA.
citing papers explorer
-
Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps
Introduces 2WikiMultiHopQA, a multi-hop QA dataset with explicit evidence chains generated via templates and Wikidata logical rules to force and evaluate multi-hop reasoning.
-
Generalizing Numerical Reasoning in Table Data through Operation Sketches and Self-Supervised Learning
TaNOS improves cross-domain numerical reasoning over tables by combining header anonymization, operation sketches, and self-supervised pretraining, achieving 80.13% accuracy on FinQA with 10% of training data.
-
RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA
RELOOP unifies retrieval across text, tables, and KGs via hierarchical sequences and dual-agent guided iteration, reporting EM/F1 gains over baselines on HotpotQA, HybridQA/TAT-QA, and MetaQA.