Progressive multimodal reasoning via active retrieval
Multi-step multimodal reasoning tasks pose significant challenges for multimodal large
language models (MLLMs), and finding effective ways to enhance their performance in such …
language models (MLLMs), and finding effective ways to enhance their performance in such …
Simrag: Self-improving retrieval-augmented generation for adapting large language models to specialized domains
Retrieval-augmented generation (RAG) enhances the question-answering (QA) abilities of
large language models (LLMs) by integrating external knowledge. However, adapting …
large language models (LLMs) by integrating external knowledge. However, adapting …
SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models
M Diao, R Li, S Liu, G Liao, J Wang, X Cai… - arXiv preprint arXiv …, 2024 - arxiv.org
As large language models (LLMs) continue to advance in capability and influence, ensuring
their security and preventing harmful outputs has become crucial. A promising approach to …
their security and preventing harmful outputs has become crucial. A promising approach to …