基于LLM相关性评分的高斯过程引导的贝叶斯主动学习用于密集段落检索
Bayesian Active Learning with Gaussian Processes Guided by LLM Relevance Scoring for Dense Passage Retrieval
AI总结：
本文提出BAGEL框架，通过高斯过程引导LLM相关性评分，解决传统方法在语义不同聚类中检索失败和相关性信号传播不足的问题，实验证明其在四个数据集上优于LLM重排序方法。
摘要：
尽管大语言模型（LLM）在零样本相关性建模方面表现出色，但其高计算成本要求将段落检索视为受预算约束的全局优化问题。现有方法被动依赖第一阶段密集检索器，导致两个局限：（1）无法检索语义不同聚类中的相关段落；（2）无法将相关性信号传播到整个语料库。为解决这些局限，我们提出贝叶斯主动学习与高斯过程相结合的BAGEL框架，通过传播稀疏LLM相关性信号来引导全局探索。BAGEL基于LLM相关性评分在整个嵌入空间中建模多模态相关性分布，随后通过策略性平衡高置信度区域的利用与不确定区域的探索来迭代选择段落进行评分。在四个基准数据集和两个LLM基础架构上的广泛实验表明，BAGEL有效探索并捕捉复杂的相关性分布，并在所有四个数据集上优于相同LLM预算下的LLM重排序方法。
英文摘要：
While Large Language Models (LLMs) exhibit exceptional zero-shot relevance modeling, their high computational cost necessitates framing passage retrieval as a budget-constrained global optimization problem. Existing approaches passively rely on first-stage dense retrievers, which leads to two limitations: (1) failing to retrieve relevant passages in semantically distinct clusters, and (2) failing to propagate relevance signals to the broader corpus. To address these limitations, we propose Bayesian Active Learning with Gaussian Processes guided by LLM relevance scoring (BAGEL), a novel framework that propagates sparse LLM relevance signals across the embedding space to guide global exploration. BAGEL models the multimodal relevance distribution across the entire embedding space with a query-specific Gaussian Process (GP) based on LLM relevance scores. Subsequently, it iteratively selects passages for scoring by strategically balancing the exploitation of high-confidence regions with the exploration of uncertain areas. Extensive experiments across four benchmark datasets and two LLM backbones demonstrate that BAGEL effectively explores and captures complex relevance distributions and outperforms LLM reranking methods under the same LLM budget on all four datasets.
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。
