4 papers
DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models
Hao Liang, Zhengyang Zhao, Meiyi Qiang +22
Data-centric training has emerged as a promising direction for improving large language models (LLMs) by optimizing not only model parameters but also the selection, composition, a…
SMA: Who Said That? Auditing Membership Leakage in Semi-Black-box RAG Controlling
Shixuan Sun, Siyuan Liang, Ruoyu Chen +3
Retrieval-Augmented Generation (RAG) and its Multimodal Retrieval-Augmented Generation (MRAG) significantly improve the knowledge coverage and contextual understanding of Large Lan…
Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025
Zonghao Ying, Siyang Wu, Run Hao +44
Multimodal Large Language Models (MLLMs) have enabled transformative advancements across diverse applications but remain susceptible to safety threats, especially jailbreak attacks…
A Framework to Assess Multilingual Vulnerabilities of LLMs
Likai Tang, Niruth Bogahawatta, Yasod Ginige +4
Large Language Models (LLMs) are acquiring a wider range of capabilities, including understanding and responding in multiple languages. While they undergo safety training to preven…