Astute rag: Overcoming imperfect retrieval augmentation and knowledge conflicts for large language models

F Wang, X Wan, R Sun, J Chen, SÖ Arık - arxiv preprint arxiv:2410.07176, 2024 - arxiv.org
Retrieval-Augmented Generation (RAG), while effective in integrating external knowledge to
address the limitations of large language models (LLMs), can be undermined by imperfect …

Language agents achieve superhuman synthesis of scientific knowledge

MD Skarlinski, S Cox, JM Laurent, JD Braza… - arxiv preprint arxiv …, 2024 - arxiv.org
Language models are known to hallucinate incorrect information, and it is unclear if they are
sufficiently accurate and reliable for use in scientific research. We developed a rigorous …

A survey on data synthesis and augmentation for large language models

K Wang, J Zhu, M Ren, Z Liu, S Li, Z Zhang… - arxiv preprint arxiv …, 2024 - arxiv.org
The success of Large Language Models (LLMs) is inherently linked to the availability of vast,
diverse, and high-quality data for training and evaluation. However, the growth rate of high …

Lightrag: Simple and fast retrieval-augmented generation

Z Guo, L **a, Y Yu, T Ao, C Huang - 2024 - openreview.net
Retrieval-Augmented Generation (RAG) systems enhance large language models (LLMs)
by integrating external knowledge sources, enabling more accurate and contextually …

Sfr-rag: Towards contextually faithful llms

XP Nguyen, S Pandit, S Purushwalkam, A Xu… - arxiv preprint arxiv …, 2024 - arxiv.org
Retrieval Augmented Generation (RAG), a paradigm that integrates external contextual
information with large language models (LLMs) to enhance factual accuracy and relevance …

Chatqa 2: Bridging the gap to proprietary llms in long context and rag capabilities

P Xu, W **, X Wu, C Xu, Z Liu, M Shoeybi… - arxiv preprint arxiv …, 2024 - arxiv.org
In this work, we introduce ChatQA 2, an Llama 3.0-based model with a 128K context
window, designed to bridge the gap between open-source LLMs and leading proprietary …

RadioRAG: Factual Large Language Models for Enhanced Diagnostics in Radiology Using Dynamic Retrieval Augmented Generation

ST Arasteh, M Lotfinia, K Bressem, R Siepmann… - arxiv preprint arxiv …, 2024 - arxiv.org
Large language models (LLMs) have advanced the field of artificial intelligence (AI) in
medicine. However LLMs often generate outdated or inaccurate information based on static …

Generating Is Believing: Membership Inference Attacks against Retrieval-Augmented Generation

Y Li, G Liu, C Wang, Y Yang - arxiv preprint arxiv:2406.19234, 2024 - arxiv.org
Retrieval-Augmented Generation (RAG) is a state-of-the-art technique that mitigates issues
such as hallucinations and knowledge staleness in Large Language Models (LLMs) by …