Log parsing converts semi-structured logs into structured templates, forming a critical foundation for downstream analysis. Traditional syntax and semantic-based parsers often struggle with semantic variations in evolving logs and data scarcity stemming from their limited domain coverage. Recent large language model (LLM)-based parsers leverage in-context learning (ICL) to extract semantics from examples, demonstrating superior accuracy. However, LLM-based parsers face two main challenges: 1) underutilization of ICL capabilities, particularly in dynamic example selection and cross-domain generalization, leading to inconsistent performance; 2) time-consuming and costly LLM querying. To address these challenges, we present MicLog, the first progressive meta in-context learning (ProgMeta-ICL) log parsing framework that combines meta-learning with ICL on small open-source LLMs (i.e., Qwen-2.5-3B). Specifically, MicLog: i) enhances LLMs' ICL capability through a zero-shot to k-shot ProgMeta-ICL paradigm, employing weighted DBSCAN candidate sampling and enhanced BM25 demonstration selection; ii) accelerates parsing via a multi-level pre-query cache that dynamically matches and refines recently parsed templates. Evaluated on Loghub-2.0, MicLog achieves 10.3% higher parsing accuracy than the state-of-the-art parser while reducing parsing time by 42.4%.

翻译：日志解析将半结构化日志转换为结构化模板，是下游分析的关键基础。传统基于语法和语义的解析器常因演化日志中的语义变异及其有限领域覆盖导致的数据稀缺而表现不佳。近期基于大语言模型（LLM）的解析器利用上下文学习（ICL）从示例中提取语义，展现出卓越的准确性。然而，LLM解析器面临两大挑战：1）ICL能力未充分利用，特别是在动态示例选择与跨领域泛化方面，导致性能不稳定；2）LLM查询耗时且成本高昂。为解决这些问题，我们提出MicLog——首个在小规模开源LLM（即Qwen-2.5-3B）上结合元学习与ICL的渐进式元上下文学习（ProgMeta-ICL）日志解析框架。具体而言，MicLog：i）通过零样本到k样本的ProgMeta-ICL范式增强LLM的ICL能力，采用加权DBSCAN候选采样与增强型BM25示例选择；ii）通过多级预查询缓存动态匹配并优化近期解析模板，从而加速解析过程。在Loghub-2.0数据集上的评估表明，MicLog比当前最优解析器提升10.3%的解析准确率，同时减少42.4%的解析时间。