arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.16932cs.IRcs.AI
收藏

RankEvolve: 通过LLM驱动的进化自动发现检索算法

RankEvolve: Automating the Discovery of Retrieval Algorithms via LLM-Driven Evolution

Santa Clara University Santa Clara CA USA;Independent Researcher Bothell WA USA;Santa Clara University;Independent Researcher

Jinming Nian, Fangchen Li, Dae Hoon Park, Yi Fang

AI总结:

RankEvolve通过LLM驱动的进化方法自动发现改进的检索算法,展示了在多个基准测试中的有效性。

摘要:

检索算法如BM25和带有Dirichlet平滑的查询似然仍保持强大且高效的首阶段排序器,但改进大多依赖于参数调优和人类直觉。我们探讨是否可以通过一个由评估器和进化搜索引导的大语言模型自动发现改进的词法检索算法。我们介绍了RankEvolve,一种基于AlphaEvolve的程序进化设置,在其中候选排序算法被表示为可执行代码,并通过在12个IR数据集(来自BEIR和BRIGHT)上的检索性能进行迭代突变、重组和选择。RankEvolve从两个种子程序开始:BM25和带有Dirichlet平滑的查询似然。进化出的算法是新颖且有效的,并在完整的BEIR和BRIGHT基准以及TREC DL 19和20上显示出有前途的转移能力。我们的结果表明,由评估器引导的LLM程序进化是自动发现新排序算法的可行路径。

英文摘要:

Retrieval algorithms like BM25 and query likelihood with Dirichlet smoothing remain strong and efficient first-stage rankers, yet improvements have mostly relied on parameter tuning and human intuition. We investigate whether a large language model, guided by an evaluator and evolutionary search, can automatically discover improved lexical retrieval algorithms. We introduce RankEvolve, a program evolution setup based on AlphaEvolve, in which candidate ranking algorithms are represented as executable code and iteratively mutated, recombined, and selected based on retrieval performance across 12 IR datasets from BEIR and BRIGHT. RankEvolve starts from two seed programs: BM25 and query likelihood with Dirichlet smoothing. The evolved algorithms are novel, effective, and show promising transfer to the full BEIR and BRIGHT benchmarks as well as TREC DL 19 and 20. Our results suggest that evaluator-guided LLM program evolution is a practical path towards automatic discovery of novel ranking algorithms.

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。

↑