发表机构
The Hong Kong University of Science and Technology (Guangzhou); University of Macau; Institute of Artificial Intelligence (TeleAI), China Telecom（香港科技大学（广州）; 澳门大学; 中国电信人工智能研究院（TeleAI））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
FCPRAG是一种融合控制的参数化RAG框架，通过轻量控制器实现样本级适配器融合，在多个数据集和LLM主干上提升了RAG的F1值，降低调优成本并增强鲁棒性。
AI 中文摘要
参数化检索增强生成（PRAG）通过针对特定段落的LoRA适配器将检索到的证据注入大型语言模型（LLM），减少对长上下文提示的依赖。然而，当为同一查询检索到多个段落时，证据级融合成为瓶颈：等权重合并会放大薄弱或相互冲突的证据，而将检索信号转化为融合权重往往需要脆弱的全局调优。我们提出FCPRAG，一种融合控制的参数化RAG框架，它添加了一个轻量控制器，用于实现检索条件下的样本级适配器融合。该控制器预测每个段落的融合分数以及样本级校准信号，包括混合门和自适应温度，使融合在信息丰富的检索信号下保持选择性，在不确定性下保持保守性。FCPRAG使用仅来自训练数据的、源自多适配器合并中每个适配器边际贡献的合并感知监督进行训练。我们进一步表明，在异方差检索不确定性下，单一数据集级温度并非最优，这推动了样本级自适应。在HotpotQA、2WikiMultiHopQA、PopQA和ComplexWebQuestions（CWQ）四个数据集上，针对三个LLM主干的实验表明，FCPRAG相比标准RAG和参数化RAG基线始终提升F1值，在2WikiMultiHopQA上的提升可达4.65%，在CWQ上可达7.55%，同时还降低了调优成本并提高了检索扰动下的鲁棒性。
英文摘要
Parametric retrieval-augmented generation (PRAG) injects retrieved evidence into a large language model (LLM) through passage-specific LoRA adapters, reducing reliance on long in-context prompts. When multiple passages are retrieved for the same query, however, evidence-level fusion becomes a bottleneck: equal-weight merging can amplify weak or conflicting evidence, and translating retrieval signals into fusion weights often requires fragile global tuning. We propose FCPRAG, a fusion-controlled parametric RAG framework that adds a lightweight controller for retrieval-conditioned, sample-level adapter fusion. The controller predicts per-passage fusion scores together with sample-level calibration signals, including a mixing gate and an adaptive temperature, enabling fusion that stays selective under informative retrieval signals and conservative under uncertainty. FCPRAG is trained with merge-aware supervision derived from each adapter's marginal contribution within a multi-adapter merge, using training data only. We further show that a single dataset-level temperature is suboptimal under heteroscedastic retrieval uncertainty, motivating sample-level adaptation. Experiments on HotpotQA, 2WikiMultiHopQA, PopQA, and ComplexWebQuestions (CWQ) across three LLM backbones show that FCPRAG consistently improves F1 over standard RAG and parametric RAG baselines, with gains of up to 4.65% on 2WikiMultiHopQA and 7.55% on CWQ, while also reducing tuning cost and improving robustness under retrieval perturbations.
CommentsAccepted to EMNLP 2026
