Work

FCPRAG: Fusion-Controller Parametric Retrieval-Augmented Generation for Stable Multi-Passage LoRA Injection

Year: 2026

Type: conference-paper

Abstract: Parametric retrieval-augmented generation (PRAG) injects retrieved evidence into a large language model (LLM) through passagespecific 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 retrievalconditioned, 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 multiadapter 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, 2Wiki-MultiHopQA, 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 2WikiMulti-HopQA and 7.55% on CWQ, while also reducing tuning cost and improving robustness under retrieval perturbations.Code is available at https://github.com/ReinerBRO/FCPRAG.

Source: Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)

DOI: 10.18653/2026.findings-emnlp.1473