Retrieval-Augmented Generation (RAG) improves factuality but retrieving for every query often hurts quality while inflating tokens and latency. We propose Training-free Adaptive Retrieval Gating (TARG), a single-shot policy that decides when to retrieve using only a short, no-context draft from the base model. From the draft's prefix logits, TARG computes lightweight uncertainty scores-mean token entropy, a margin signal derived from the top-1/top-2 logit gap via a monotone link, or small-N variance across a handful of stochastic prefixes-and triggers retrieval only when the score exceeds a threshold. The gate is model-agnostic, adds only tens to hundreds of draft tokens, and requires no additional training or auxiliary heads. On five QA benchmarks spanning short-answer (NQ-Open, TriviaQA, PopQA), multi-hop (MuSiQue), and long-form (ASQA) tasks, TARG consistently pushes the accuracy-efficiency frontier: compared with Alway-RAG, TARG matches or improves EM/F1 while reducing retrieval by 70-90% and cutting end-to-end latency, and it remains close to Never-RAG in overhead. A central empirical finding is that under modern instruction-tuned LLMs the margin signal is a robust default (entropy compresses as backbones sharpen), with small-N variance offering a conservative, budget-first alternative. We provide ablations over gate type and prefix length and use a $Δ$-latency view to make budget trade-offs explicit.

翻译：检索增强生成（RAG）提升了事实准确性，但为每个查询都进行检索往往损害生成质量，同时增加词元数量与延迟。我们提出免训练自适应检索门控（TARG），这是一种单次策略，仅利用基座模型生成的简短无上下文草稿，即可决策何时需要检索。基于草稿前缀的logits值，TARG计算轻量级不确定性得分——包括均值词元熵、通过单调链接函数从top-1/top-2 logits差值导出的边际信号，或少量随机前缀的弱小样本方差——仅当得分超过阈值时触发检索。该门控与模型无关，仅需添加数十至数百个草稿词元，且无需额外训练或辅助网络头。在涵盖短答案（NQ-Open、TriviaQA、PopQA）、多跳（MuSiQue）和长文本（ASQA）的五项QA基准测试中，TARG持续推动准确率-效率前沿：与始终检索策略相比，TARG在匹配或提升EM/F1的同时，将检索量减少70-90%并降低端到端延迟，其额外开销接近无检索策略。核心实验发现是：在现代指令微调大语言模型下，边际信号成为稳健的默认选择（随着基座模型输出趋近确定，熵值被压缩），而弱小样本方差则提供保守的预算优先替代方案。我们针对门控类型与前缀长度进行消融实验，并采用Δ-延迟视角显式呈现预算权衡。