RoseRAG: Robust Retrieval-augmented Generation with Small-scale LLMs via Margin-aware Preference Optimization
Year: 2025
Type: conference-paper
Abstract: Large language models (LLMs) have achieved impressive performance but face high computational costs and latency, limiting their deployment in resource-constrained settings.In contrast, small-scale LLMs (SLMs) are more efficient yet struggle to capture evolving realworld knowledge.Retrieval-augmented generation (RAG) helps by integrating external knowledge, but imperfect retrieval can introduce distracting noise that misleads SLMs.We propose ROSERAG, a robust RAG framework for SLMs via Margin-aware Preference Optimization.ROSERAG employs multi-turn prompting for detailed reasoning, rejection sampling for high-quality explanations, and contrastive preference selection to refine responses by maximizing the likelihood gap between preferred and non-preferred outputs.By integrating these components into a margin-aware optimization process, ROSERAG robustly enhances the accuracy and reliability of SLMs for RAG applications.Extensive experiments on three opendomain question answering benchmarks indicate that our innovative ROSERAG surpasses state-of-the-art baselines significantly.
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W4412888222