用大模型自动进化出更优的检索算法，无需人工调参。
RankEvolve: Automating the Discovery of Retrieval Algorithms via LLM-Driven Evolution
- 用大模型+进化算法自动生成可执行的检索代码
- 在12个数据集上超越BM25和查询概率模型
- 适合对自动算法设计感兴趣的科研与工程人员
BM25和带狄利克雷平滑的查询似然等检索算法仍是高效的一阶段排序器，但改进主要依赖参数调优和人工直觉。我们探究是否可通过大语言模型，在评估器引导和进化搜索下自动发现更优的词法检索算法。提出RankEvolve，基于AlphaEvolve的程序进化框架，候选排序算法以可执行代码形式表示，并根据在BEIR和BRIGHT的12个信息检索数据集上的表现进行迭代变异、重组和选择。起始种子为BM25和带狄利克雷平滑的查询似然。演化出的算法新颖且有效，在完整BEIR、BRIGHT以及TREC DL 19和20基准上均展现良好泛化能力。结果表明，评估器引导的大型语言模型程序进化是自动发现新型排序算法的可行路径。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。