Retrieval-augmented generation for natural language processing: A survey

S Wu, Y **ong, Y Cui, H Wu, C Chen, Y Yuan… - arxiv preprint arxiv …, 2024 - arxiv.org
Large language models (LLMs) have demonstrated great success in various fields,
benefiting from their huge amount of parameters that store knowledge. However, LLMs still …

Fine-tuning image transformers using learnable memory

M Sandler, A Zhmoginov… - Proceedings of the …, 2022 - openaccess.thecvf.com
In this paper we propose augmenting Vision Transformer models with learnable memory
tokens. Our approach allows the model to adapt to new tasks, using few parameters, while …

Graphreader: Building graph-based agent to enhance long-context abilities of large language models

S Li, Y He, H Guo, X Bu, G Bai, J Liu, J Liu, X Qu… - arxiv preprint arxiv …, 2024 - arxiv.org
Long-context capabilities are essential for large language models (LLMs) to tackle complex
and long-input tasks. Despite numerous efforts made to optimize LLMs for long contexts …