5 papers
Mitigating Jailbreaks with Intent-Aware LLMs
Wei Jie Yeo, Ranjan Satapathy, Erik Cambria
Despite extensive safety-tuning, large language models (LLMs) remain vulnerable to jailbreak attacks via adversarially crafted instructions, reflecting a persistent trade-off betwe…
Understanding Refusal in Language Models with Sparse Autoencoders
Wei Jie Yeo, Nirmalendu Prakash, Clement Neo +3
Refusal is a key safety behavior in aligned language models, yet the internal mechanisms driving refusals remain opaque. In this work, we conduct a mechanistic study of refusal in…
Debiasing CLIP: Interpreting and Correcting Bias in Attention Heads
Wei Jie Yeo, Rui Mao, Moloud Abdar +2
Multimodal models like CLIP have gained significant attention due to their remarkable zero-shot performance across various tasks. However, studies have revealed that CLIP can inadv…
Self-training Large Language Models through Knowledge Detection
Wei Jie Yeo, Teddy Ferdinan, Przemyslaw Kazienko +2
Large language models (LLMs) often necessitate extensive labeled datasets and training compute to achieve impressive performance across downstream tasks. This paper explores a self…
Towards Faithful Natural Language Explanations: A Study Using Activation Patching in Large Language Models
Wei Jie Yeo, Ranjan Satapathy, Erik Cambria
Large Language Models (LLMs) are capable of generating persuasive Natural Language Explanations (NLEs) to justify their answers. However, the faithfulness of these explanations sho…