Wei Jie Yeo — accepted AI-conference papers

2025

Towards Faithful Natural Language Explanations: A Study Using Activation Patching in Large Language Models

Wei Jie Yeo, Ranjan Satapathy, Erik Cambria

EMNLP 2025

Large Language Models (LLMs) are capable of generating persuasive Natural Language Explanations (NLEs) to justify their answers. However, the faithfulness of these explanations should not be readily trusted at face value. Recent studies have proposed various methods to measure the faithfulness of NL

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

Understanding Refusal in Language Models with Sparse Autoencoders

Wei Jie Yeo, Nirmalendu Prakash, Clement Neo, Ranjan Satapathy, Roy Ka-Wei Lee, Erik Cambria

EMNLP 2025

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 instruction-tuned LLMs using sparse autoencoders to identify latent features that causally mediate refusal behaviors. We

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗