Federated Learning With Ad-hoc Adapter Insertions: The Case Of Soft-embeddings For Training Classifier-as-retriever

Abstract

When existing retrieval-augmented generation (RAG) solutions are intended to be used for new knowledge domains, it is necessary to update their encoders, which are taken to be pretrained large language models (LLMs). However, fully finetuning these large models is compute- and memory-intensive, and even infeasible when deployed on resource-constrained edge devices. We propose a novel encoder architecture in this work that addresses this limitation by using a frozen small language model (SLM), which satisfies the memory constraints of edge devices, and inserting a small adapter network before the transformer blocks of the SLM. The trainable adapter takes the token embeddings of the new corpus and learns to produce enhanced soft embeddings for it, while requiring significantly less compute power to update than full fine-tuning. We further propose a novel retrieval mechanism by attaching a classifier head to the SLM encoder, which is trained to learn a similarity mapping of the input embe

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyfofonjka2025federated

Related papers

• Align Then Train: Efficient Retrieval Adapter Learning (2026)0.00
• LMAR: Language Model Augmented Retriever For Domain-specific Knowledge Indexing (2025)1.57
• Search-adaptor: Embedding Customization For Information Retrieval (2023)0.00
• Parameter-efficient Sparse Retrievers And Rerankers Using Adapters (2023)4.52
• Matryoshka-adaptor: Unsupervised And Supervised Tuning For Smaller Embedding Dimensions (2024)2.26
• Freeret: Mllms As Training-free Retrievers (2025)0.00
• Lexsembridge: Fine-grained Dense Representation Enhancement Through Token-aware Embedding Augmentation (2025)2.35
• RRRA: Resampling And Reranking Through A Retriever Adapter (2025)0.00