6 papers
SEATauBench: Adapting Tool-Agent-User Evaluation Into Low-Resource Southeast Asian Languages
My Chiffon Nguyen, Aulia Adila, Saksorn Ruangtanusak +4
While AI development and evaluation for Southeast Asia (SEA) has grown rapidly, agent capabilities in regional languages are still poorly understood despite its importance to sover…
Exploring Extrinsic and Intrinsic Properties for Effective Reasoning with Code Interpreter
Patomporn Payoungkhamdee, Napat Laosaengpha, Jenta Wonglertsakul +8
Reasoning with a Code Interpreter (CI) has emerged as an effective paradigm for enhancing the reasoning capabilities of large language models (LLMs) through executable computation…
DuDi: Dual-Signal Distillation with Cross-Lingual Verbalizer
Patomporn Payoungkhamdee, Tinnakit Udsa, Jian Gang Ngui +3
Small language models (SLMs) are efficient and scalable, but their multilingual capabilities degrade severely at sub-billion scales, especially for Southeast Asian (SEA) languages.…
Exploring Cross-Client Memorization of Training Data in Large Language Models for Federated Learning
Tinnakit Udsa, Can Udomcharoenchaikit, Patomporn Payoungkhamdee +2
Federated learning (FL) enables collaborative training without raw data sharing, but still risks training data memorization. Existing FL memorization detection techniques focus on…
Distilling Multilingual Vision-Language Models: When Smaller Models Stay Multilingual
Sukrit Sriratanawilai, Jhayahgrit Thongwat, Romrawin Chumpu +3
Vision-language models (VLMs) exhibit uneven performance across languages, a problem that is often exacerbated when the model size is reduced. While Knowledge distillation (KD) dem…
Towards Better Understanding of Program-of-Thought Reasoning in Cross-Lingual and Multilingual Environments
Patomporn Payoungkhamdee, Pume Tuchinda, Jinheon Baek +6
Multi-step reasoning is essential for large language models (LLMs), yet multilingual performance remains challenging. While Chain-of-Thought (CoT) prompting improves reasoning, it…