研究人员开发了新的方法来改进搜索结果的重排，特别是在零资源场景下，传统监督训练不可行。一种方法DART，通过初始检索中的伪阳性和伪阴性示例在推理时自适应评分函数，以最小的延迟提高性能。另一种方法利用长上下文语言模型一次性处理整个候选段落集，从而实现更有效和高效的重排。第三种技术利用小型语言模型特定层的注意力分数来估计段落-查询相关性，在LoCoMo等基准测试上取得了最先进的成果。 AI
影响 这些进展可以显著提高搜索系统的准确性和效率，尤其是在专业或低资源领域。
排序理由 多篇学术论文提出了信息检索重排的新方法。
在 arXiv cs.IR (Information Retrieval) 阅读 →
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
arXiv:2606.01070v1 Announce Type: cross Abstract: Dense retrievers excel at first-stage candidate generation but lack effective reranking in zero-resource settings. Existing approaches face a fundamental dilemma: cross-encoders deliver strong reranking quality but require costly …
Previous LLM-based passage re-rankers are often expensive and slow because the input context constraints require the LLM to make many dependent model calls. We study how recent long-context LLMs change this problem: when the full set of retrieved candidate passages can be shown t…
arXiv:2602.12192v3 Announce Type: replace Abstract: Built upon the existing analysis of retrieval heads in large language models, we propose an alternative reranking framework that trains models to estimate passage-query relevance using the attention scores of selected heads. Thi…
Dense retrievers excel at first-stage candidate generation but lack effective reranking in zero-resource settings. Existing approaches face a fundamental dilemma: cross-encoders deliver strong reranking quality but require costly supervised training and incur high latency, while …