24 citations · 39 across the 12 of their papers we have counts for
12 papers
Geometry-Aware CLIP Retrieval via Local Cross-Modal Alignment and Steering
Nirmalendu Prakash, Narmeen Fatimah Oozeer, Xin Su +8
CLIP retrieval is typically framed as a pointwise similarity problem in a shared embedding space. While CLIP achieves strong global cross-modal alignment, many retrieval failures a…
DreamReader: An Interpretability Toolkit for Text-to-Image Models
Nirmalendu Prakash, Narmeen Oozeer, Michael Lan +6
Despite the rapid adoption of text-to-image (T2I) diffusion models, causal and representation-level analysis remains fragmented and largely limited to isolated probing techniques.…
Beyond I'm Sorry, I Can't: Dissecting Large Language Model Refusal
Nirmalendu Prakash, Yeo Wei Jie, Amir Abdullah +3
Refusal on harmful prompts is a key safety behaviour in instruction-tuned large language models (LLMs), yet the internal causes of this behaviour remain poorly understood. We study…
Distribution-Aware Feature Selection for SAEs
Narmeen Oozeer, Nirmalendu Prakash, Michael Lan +2
Sparse autoencoders (SAEs) decompose neural activations into interpretable features. A widely adopted variant, the TopK SAE, reconstructs each token from its K most active latents.…
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…
Activation Space Interventions Can Be Transferred Between Large Language Models
Narmeen Oozeer, Dhruv Nathawani, Nirmalendu Prakash +3
The study of representation universality in AI models reveals growing convergence across domains, modalities, and architectures. However, the practical applications of representati…
Interpreting Bias in Large Language Models: A Feature-Based Approach
Nirmalendu Prakash, Lee Ka Wei Roy
Large Language Models (LLMs) such as Mistral and LLaMA have showcased remarkable performance across various natural language processing (NLP) tasks. Despite their success, these mo…
SGHateCheck: Functional Tests for Detecting Hate Speech in Low-Resource Languages of Singapore
Ri Chi Ng, Nirmalendu Prakash, Ming Shan Hee +2
To address the limitations of current hate speech detection models, we introduce \textsf{SGHateCheck}, a novel framework designed for the linguistic and cultural context of Singapo…
Prompting Large Language Models for Topic Modeling
Han Wang, Nirmalendu Prakash, Nguyen Khoi Hoang +3
Topic modeling is a widely used technique for revealing underlying thematic structures within textual data. However, existing models have certain limitations, particularly when dea…
MATK: The Meme Analytical Tool Kit
Ming Shan Hee, Aditi Kumaresan, Nguyen Khoi Hoang +3
The rise of social media platforms has brought about a new digital culture called memes. Memes, which combine visuals and text, can strongly influence public opinions on social and…
PromptMTopic: Unsupervised Multimodal Topic Modeling of Memes using Large Language Models
Nirmalendu Prakash, Han Wang, Nguyen Khoi Hoang +2
The proliferation of social media has given rise to a new form of communication: memes. Memes are multimodal and often contain a combination of text and visual elements that convey…
TotalDefMeme: A Multi-Attribute Meme dataset on Total Defence in Singapore
Nirmalendu Prakash, Ming Shan Hee, Roy Ka-Wei Lee
Total Defence is a defence policy combining and extending the concept of military defence and civil defence. While several countries have adopted total defence as their defence pol…