Active learning rankers outperform sorting-based aggregation of noisy LLM pairwise judgments and a randomized single-call oracle removes position bias without extra queries.
Contextual Relevance and Adaptive Sampling for
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Active Learners as Efficient PRP Rerankers
Active learning rankers outperform sorting-based aggregation of noisy LLM pairwise judgments and a randomized single-call oracle removes position bias without extra queries.