让缓存智能判断答案是否过时，提升大模型检索效率与准确性
Risk-Constrained Freshness-Aware Semantic Caching for Open-Web Retrieval-Augmented LLMs
- 基于时间衰减模型+神经网络预测缓存内容过时概率
- 24小时内实现97%检索节省，过时错误率仅0.1%
- 适合对数据时效性敏感的开放网页问答系统
语义缓存通过复用相似查询的答案降低检索增强生成（RAG）的延迟与成本，但现有方法大多未考虑开放网络证据的时间动态性。本文提出FreshCache，一种三层语义缓存机制，将缓存重用视为风险约束的时间推理问题：在批准缓存命中前，利用拟合的指数衰减模型结合学习的MLP估算结果过时概率，并仅当该概率低于各层级误差预算（答案级ε=0.10，URL列表级ε=0.20，页面内容级ε=0.35）时才允许重用。这使系统能随条目老化渐进降级，而非强制选择过时命中或全链路执行。我们构建了FreshCache-Bench基准，包含8,072个基础查询，覆盖五类新鲜度，基于真实网页快照（1、12、24小时及7天后）标注过时标签，并通过改写扩展至31,201个查询。在24小时评估窗口下，FreshCache_MLP实现97%搜索API节省，哈希基过时错误率仅为0.1%；396组确认变更对的LLM判别显示，仅有34.3%的内容变化影响答案正确性，实际影响答案的过时错误率约为0.034%。规则版FreshCache在时间留出校准下实现98%节省，过时错误率为3.3%，优于SemanticTTL（14.9%过时，72%节省）、vCache（7.2%过时，47%节省）和SCALM（5.2%过时，96%节省）。消融实验表明，时间风险门控相比仅依赖相似性的重用降低11.6个百分点过时错误，学习的MLP进一步降低3.2个百分点。
原文摘要 · Abstract (English)
Semantic caching reduces the latency and cost of retrieval-augmented generation (RAG) by serving cached answers to semantically similar queries, but most existing methods do not model the time-varying freshness of open-web evidence. We present FreshCache, a three-tier semantic cache that treats cache reuse as a risk-constrained temporal inference problem: before approving a cache hit, FreshCache estimates the probability that the cached result is stale using a fitted exponential decay model enhanced by a learned MLP, and approves reuse only when that probability falls below a per-tier error budget across answers (epsilon = 0.10), URL lists (epsilon = 0.20), and page content (epsilon = 0.35). This allows the system to degrade gracefully as entries age rather than forcing a binary choice between a stale hit and a full pipeline execution. We introduce FreshCache-Bench, a benchmark of 8,072 base queries across five freshness classes with ground truth staleness labels drawn from real web snapshots at 1, 12, 24 hours, and 7 days after a baseline crawl, expanded to 31,201 queries via paraphrase generation. At the 24-hour evaluation window, FreshCache_MLP achieves 97% search API savings at 0.1% hash-based stale error, and an LLM-judge evaluation on 396 confirmed change pairs shows that only 34.3% of detected content changes actually affect answer correctness, placing true answer-affecting stale error at approximately 0.034%. The rule-based FreshCache achieves 98% search savings at 3.3% stale error under a temporal holdout calibration, outperforming SemanticTTL (14.9% stale, 72% saved), vCache (7.2% stale, 47% saved), and SCALM (5.2% stale, 96% saved). Ablations show the temporal risk gate accounts for an 11.6 point reduction in stale error over similarity-only reuse, and the learned MLP reduces stale error a further 3.2 points over the rule-based model.
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。