4 papers
Curvature-Aware Safety Restoration In LLMs Fine-Tuning
Thong Bach, Thanh Nguyen-Tang, Dung Nguyen +2
Fine-tuning Large Language Models (LLMs) for downstream tasks often compromises safety alignment, even when using parameter-efficient methods like LoRA. In this work, we uncover a…
ViConBERT: Context-Gloss Aligned Vietnamese Word Embedding for Polysemous and Sense-Aware Representations
Khang T. Huynh, Dung H. Nguyen, Binh T. Nguyen
Recent advances in contextualized word embeddings have greatly improved semantic tasks such as Word Sense Disambiguation (WSD) and contextual similarity, but most progress has been…
Rethinking Deep Alignment Through The Lens Of Incomplete Learning
Thong Bach, Dung Nguyen, Thao Minh Le +1
Large language models exhibit systematic vulnerabilities to adversarial attacks despite extensive safety alignment. We provide a mechanistic analysis revealing that position-depend…
Knowledge Consultation for Semi-Supervised Semantic Segmentation
Thuan Than, Nhat-Anh Nguyen-Dang, Dung Nguyen +7
Semi-Supervised Semantic Segmentation reduces reliance on extensive annotations by using unlabeled data and state-of-the-art models to improve overall performance. Despite the succ…