Quality–Latency Benchmarking of Log-Template Retrieval for GenAI-Assisted Operational RCA

GenAI copilots for network operations rely on rapid retrieval of historical evidence for incident triage and root cause analysis (RCA). Yet retrieval is often evaluated solely on relevance, while tail latency – a first-class QoE constraint in operator-in-the-loop workflows – is rarely reported. We benchmark retrieval of log templates used as RCA evidence units across three Loghub datasets: Blue Gene/L (BGL), HDFS, and Thunderbird. We compare BM25, dense retrieval, hybrid reciprocal rank fusion (RRF), and contextual re-ranking with temporal recency and a proxy locality prior. Dense retrieval is the strongest overall quality–latency baseline and outperforms BM25 on quality across all three datasets. On BGL, Dense attains MRR@10=0.690, nDCG@10=0.760, and P95=772 ms; on Thunderbird, Dense again leads with MAP=0.170 and Recall@10=0.160. HDFS shows the strongest contextual gains because its anomalies are tightly time-localized at the block level, unlike the more dispersed BGL and Thunderbird settings; in those settings, LAR-Rerank reaches MAP=0.624 and Recall@10=0.496. These results show that dataset structure strongly shapes the value of temporal and locality priors, while Dense remains a robust default retrieval strategy. Code: https://github.com/Mustafa3946/rca-retrieval-bench.