Set-level margin training that ranks complete gold-compatible passage sets above incomplete or noisy ones, implemented with ParaSet exploration and SetCE reranking, improves multi-hop retrieval and QA and complements document-level CE.
The margin loss in Eq
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Retrieving a Set, Not Independent Passages: Set-Level Compatibility Learning for Efficient Set Exploration
Set-level margin training that ranks complete gold-compatible passage sets above incomplete or noisy ones, implemented with ParaSet exploration and SetCE reranking, improves multi-hop retrieval and QA and complements document-level CE.