两篇新研究论文探讨了大型语言模型（LLMs）在信息检索中的应用和效率。第一篇论文是一项复现性研究，评估了十种基于LLM的查询重构方法在各种检索范式和LLM规模下的表现，发现收益高度依赖于检索方法，并且更大的模型不一定表现更好。第二篇论文介绍了ResRank，一个统一的框架，它将段落压缩成单一的嵌入向量，用于高效的列表重排序，解决了将全文输入LLM相关的延迟瓶颈和质量下降问题。 AI
影响 这些研究强调了仔细评估LLM在检索中有效性的必要性，并提出了更高效的基于LLM的重排序方法。
排序理由 该集群包含两篇讨论LLM在信息检索中应用的学术论文，并提出了新的框架。
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
arXiv:2604.27421v1 Announce Type: cross Abstract: Large Language Models (LLMs) are now widely used for query reformulation and expansion in Information Retrieval, with many studies reporting substantial effectiveness gains. However, these results are typically obtained under hete…
Large Language Models (LLMs) are now widely used for query reformulation and expansion in Information Retrieval, with many studies reporting substantial effectiveness gains. However, these results are typically obtained under heterogeneous experimental conditions, making it diffi…
arXiv:2604.22180v1 Announce Type: cross Abstract: Large language model (LLM) based listwise reranking has emerged as the dominant paradigm for achieving state-of-the-art ranking effectiveness in information retrieval. However, its reliance on feeding full passage texts into the L…
Large language model (LLM) based listwise reranking has emerged as the dominant paradigm for achieving state-of-the-art ranking effectiveness in information retrieval. However, its reliance on feeding full passage texts into the LLM introduces two critical bottlenecks: the "lost …