| title | Active Learners as Efficient PRP Rerankers |
|---|---|
| authors | Jeremías Figueiredo Paschmann, Juan Kaplan, Francisco Nattero, Santiago Barron, Juan Wisznia, Luciano del Corro |
| date | 2026-05-15 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.14236 |
| affiliation | Universidad de San Andrés |
| upvotes | 77 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Pairwise Ranking Prompting (PRP) elicits pairwise preference judgments from an LLM, which are then aggregated into a ranking, usually via classical sorting algorithms. However, judgments are noisy, order-sensitive, and sometimes intransitive, so sorting assumptions do not match the setting. Because sorting aims to recover a full permutation, truncating it to meet a call budget does not produce a dependable top-K. We thus reframe PRP reranking as active learning from noisy pairwise comparisons and show that active rankers are drop-in replacements that improve NDCG@10 per call in the call-constrained regime. Our noise-robust framework also introduces a randomized-direction oracle that uses a single LLM call per pair. This approach converts systematic position bias into zero-mean noise, enabling unbiased aggregate ranking without the cost of bidirectional calls. |
cite
@misc{paschmann2026active,
title={Active Learners as Efficient PRP Rerankers},
author={Jeremías Figueiredo Paschmann and Juan Kaplan and Francisco Nattero and Santiago Barron and Juan Wisznia and Luciano del Corro},
year={2026},
eprint={2605.14236},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.14236}
}