arXiv:2606. 31087v1 Announce Type: cross Abstract: Few-shot selection typically assumes that reranking retrieved examples always improves performance.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2606. 01070v1 Announce Type: cross Abstract: Dense retrievers excel at first-stage candidate generation but lack effective reranking in zero-resource settings.
arXiv:2606. 27997v1 Announce Type: new Abstract: Benchmarks of machine learning models often include many datasets, making evaluation expensive.
arXiv:2606. 15216v1 Announce Type: cross Abstract: Diversity plays a critical role in data selection, improving performance under fixed data budgets by reducing redundancy and repetition.
arXiv:2606. 05308v1 Announce Type: new Abstract: With PRECISE, we extended Prediction-Powered Inference to produce bias-corrected estimates of ranking evaluation metrics by combining a small human-labeled set with a large LLM-judged set.
arXiv:2607. 16259v1 Announce Type: new Abstract: Pretrained models are typically ranked on multi-task leaderboards to assess their effectiveness across diverse tasks.
arXiv:2605. 04495v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) relies on evidence ranking to determine what information is exposed to the generator, yet existing retrieval and reranking methods primarily estimate query--document relevance.