DualEnd enables whole-pool setwise reranking of 100 candidates using 50 serial LLM calls by simultaneously selecting top and bottom passages with long-context models.
arXiv preprint arXiv:2602.03422 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Whole-Pool Setwise Reranking with Long-Context Language Models
DualEnd enables whole-pool setwise reranking of 100 candidates using 50 serial LLM calls by simultaneously selecting top and bottom passages with long-context models.