LAAM 混合检索框架：用主动学习逼近 LLM 排序，能耗降至 3.3%
Active Learning of Approximate LLM Ranking for Energy-Efficient Retrieval of Long Queries
搞检索的同学可以看看这篇：LAAM 用主动学习只挑最关键的文档丢给 DeepSeek v3 打分，能耗只要全量重排的 3.3%，精度还能保住 87% 的 P@10。想自建 RAG 或搜索又心疼 LLM 调用成本的团队，这套能耗-精度可调的思路很实用。
一篇 arXiv 论文提出 LLM Active Approximation Model（LAAM），在语义检索与 LLM 重排之间加入一个轻量学习预测器作为中介。框架通过主动学习循环让 LLM 只标注少量最具信息量的文档，从而大幅降低推理成本。
在 TREC Robust 2004 数据集上，作者使用 Lucene 的 BM25 检索和 DeepSeek v3 作为 LLM，在三种查询冗长度下评测。对冗长查询，LAAM 达到 DeepSeek 重排平均 P@10 的 87%（0.459 vs 0.526），而每查询能耗仅需 3.3%。
统计检验显示 LAAM 显著优于 BM25，且在平均准确率上与 DeepSeek 无显著差异（Friedman 检验 P<0.05 加事后检验），但 MAP 上未达同等水平。该框架在能耗-精度曲线上提供连续可调的操作点，让开发者按计算预算选择检索质量。
Active Learning of Approximate LLM Ranking for Energy-Efficient Retrieval of Long Queries
Search engines and Large Language Models (LLMs) offer complementary strengths for document retrieval: lexical retrievers which rely on keyword matching are fast and energy-efficient, whereas LLMs capture semantic meaning and excel at interpreting long, context-rich queries. However, this comes at a cost that is computationally and energetically prohibitive. We propose the LLM Active Approximation Model (LAAM), a hybrid retrieval framework that introduces a lightweight learned predictor which serves as an intermediary between semantic retrieval and LLM retrieval. LAAM is refined through an active learning loop where an LLM labels a small number of documents. By concentrating LLM evaluations on the most informative documents, the framework substantially reduces inference cost while preserving retrieval effectiveness. We evaluate the proposed framework on TREC Robust 2004 using Lucene with BM25 retrieval and DeepSeek v3 as the LLM, under three levels of query verbosity. For verbose queries, LAAM achieves 87% of average P@10 achieved by DeepSeek's reranking (0.459 vs. 0.526), while requiring only 3.3% of the per-query energy consumption. LAAM is statistically significantly better than BM25 and is indistinguishable from DeepSeek on average precision, though not on MAP (Friedman test, P<0.05 with post-hoc testing). Overall, our results demonstrate that selectively approximating LLM relevance judgments through active learning enables retrieval accuracy to be controlled directly through the evaluation (and consequently energy) budget. Rather than committing to either inexpensive (and less accurate) lexical retrieval or exhaustive (and expensive) LLM reranking, our framework exposes a continuous spectrum of operating points along the energy--accuracy curve, allowing practitioners to select how to trade retrieval quality with computational budget.
This report is categorized under AITOP's "Papers" desk. Key entities and technical topics under continuous tracking include DeepSeek v3, LAAM, BM25, RAG.
Primary source verification: published directly by arXiv: DeepSeek with first-party authority.