4 papers · 1 filter
Adversarial Defence without Adversarial Defence: Enhancing Language Model Robustness via Instance-level Principal Component Removal
Yang Wang, Chenghao Xiao, Yizhi Li +3
Pre-trained language models (PLMs) have driven substantial progress in natural language processing but remain vulnerable to adversarial attacks, raising concerns about their robust…
Early Detection and Reduction of Memorisation for Domain Adaptation and Instruction Tuning
Dean L. Slack, Noura Al Moubayed
Although large language models excel across many tasks, they can memorise training data and thereby expose private or copyrighted text. Most defences target the pre-training stage,…
Analyzing LLMs' Knowledge Boundary Cognition Across Languages Through the Lens of Internal Representations
Chenghao Xiao, Hou Pong Chan, Hao Zhang +4
While understanding the knowledge boundaries of LLMs is crucial to prevent hallucination, research on the knowledge boundaries of LLMs has predominantly focused on English. In this…
X-ray Made Simple: Lay Radiology Report Generation and Robust Evaluation
Kun Zhao, Chenghao Xiao, Sixing Yan +5
Radiology Report Generation (RRG) has advanced considerably with the development of multimodal generative models. Despite the progress, the field still faces significant challenges…