ReBOL：通过批量LLM相关性观察和查询重述进行检索
ReBOL: Retrieval via Bayesian Optimization with Batched LLM Relevance Observations and Query Reformulation
AI总结：
ReBOL通过引入多模态贝叶斯优化和查询重述技术，改进检索阶段的召回率和排名质量，优于现有LLM重排序基线。
摘要：
LLM重排序受限于向量相似性检索的top-k文档，无法捕捉上下文查询-文档token交互或多模态相关性分布。我们提出ReBOL，通过LLM查询重述初始化多模态贝叶斯优化后验，迭代获取文档批次进行LLM查询-文档相关性评分，并更新后验以优化相关性。实验表明，ReBOL在五个BEIR数据集上实现了更高的召回率和竞争性的排名，例如在Robust04数据集上，召回率@100为46.5% vs 35.0%，NDCG@10为63.6% vs 61.2%。此外，ReBOL的延迟与LLM重排序器相当。
英文摘要：
LLM-reranking is limited by the top-k documents retrieved by vector similarity, which neither enables contextual query-document token interactions nor captures multimodal relevance distributions. While LLM query reformulation attempts to improve recall by generating improved or additional queries, it is still followed by vector similarity retrieval. We thus propose to address these top-k retrieval stage failures by introducing ReBOL, which 1) uses LLM query reformulations to initialize a multimodal Bayesian Optimization (BO) posterior over document relevance, and 2) iteratively acquires document batches for LLM query-document relevance scoring followed by posterior updates to optimize relevance. After exploring query reformulation and document batch diversification techniques, we evaluate ReBOL against LLM reranker baselines on five BEIR datasets and using two LLMs (Gemini-2.5-Flash-Lite, GPT-5.2). ReBOL consistently achieves higher recall and competitive rankings, for example compared to the best LLM reranker on the Robust04 dataset with 46.5% vs. 35.0% recall@100 and 63.6% vs. 61.2% NDCG@10. We also show that ReBOL can achieve comparable latency to LLM rerankers.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
