5 papers
Scenario-based Probing and Steering Cultural Values in Large Language Models--Extended Version
Trung Duc Anh Dang, Tung Kieu, Sarah Masud
Large Language Models (LLMs) are deployed across cultural contexts but often reflect homogenized values inherited from training data. Evaluations of cultural alignment typically re…
Cultural Value Alignment Via Latent Activation Steering in Large Language Models
Trung Duc Anh Dang, Sarah Masud
Large Language Models (LLMs) often exhibit homogenized cultural perspectives. While the World Values Survey (WVS) provides a gold standard for mapping human values, traditional dir…
SAMix: Calibrated and Accurate Continual Learning via Sphere-Adaptive Mixup and Neural Collapse
Trung-Anh Dang, Vincent Nguyen, Ngoc-Son Vu +1
While most continual learning methods focus on mitigating forgetting and improving accuracy, they often overlook the critical aspect of network calibration, despite its importance.…
GemDetox at TextDetox CLEF 2025: Enhancing a Massively Multilingual Model for Text Detoxification on Low-resource Languages
Trung Duc Anh Dang, Ferdinando Pio D'Elia
As social-media platforms emerge and evolve faster than the regulations meant to oversee them, automated detoxification might serve as a timely tool for moderators to enforce safe…
Memory-efficient Continual Learning with Neural Collapse Contrastive
Trung-Anh Dang, Vincent Nguyen, Ngoc-Son Vu +1
Contrastive learning has significantly improved representation quality, enhancing knowledge transfer across tasks in continual learning (CL). However, catastrophic forgetting remai…