RAVEN: In-context Learning With Retrieval-augmented Encoder-decoder Language Models

Abstract

In this paper, we investigate the in-context learning ability of retrieval-augmented encoder-decoder language models. We first conduct a comprehensive analysis of existing models and identify their limitations in in-context learning, primarily due to a mismatch between pretraining and inference, as well as a restricted context length. To address these issues, we propose RAVEN, a model that combines retrieval-augmented masked language modeling and prefix language modeling. We further introduce Fusion-in-Context Learning to enhance the few-shot performance by enabling the model to leverage more in-context examples without requiring additional training. Through extensive experiments, we demonstrate that our simple yet effective design significantly improves performance, achieving results comparable to the most advanced language models in certain scenarios, despite having substantially fewer parameters. Our work underscores the potential of retrieval-augmented encoder-decoder language mode

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhuang2023raven

Related papers

• RAVEN: Multitask Retrieval Augmented Vision-language Learning (2024)0.00
• Rare: Retrieval Augmented Retrieval With In-context Examples (2024)0.00
• RAVENEA: A Benchmark For Multimodal Retrieval-augmented Visual Culture Understanding (2025)0.00
• Revela: Dense Retriever Learning Via Language Modeling (2025)0.00
• CODER: An Efficient Framework For Improving Retrieval Through Contextual Document Embedding Reranking (2021)7.16
• Xrag: Extreme Context Compression For Retrieval-augmented Generation With One Token (2024)7.81
• Rzenembed: Towards Comprehensive Multimodal Retrieval (2025)0.00
• Llm-augmented Retrieval: Enhancing Retrieval Models Through Language Models And Doc-level Embedding (2024)0.00