4 papers
The Atomic Instruction Gap: Instruction-Tuned LLMs Struggle with Simple, Self-Contained Directives
Henry Lim, Kwan Hui Lim
Instruction-tuned large language models (IT-LLMs) exhibit strong zero-shot reasoning, yet their ability to execute simple, self-contained instructions remains underexplored, despit…
Physics-Informed Autonomous LLM Agents for Explainable Power Electronics Modulation Design
Junhua Liu, Fanfan Lin, Xinze Li +2
LLM-based autonomous agents have recently shown strong capabilities in solving complex industrial design tasks. However, in domains aiming for carbon neutrality and high-performanc…
From Intents to Conversations: Generating Intent-Driven Dialogues with Contrastive Learning for Multi-Turn Classification
Junhua Liu, Yong Keat Tan, Bin Fu +1
In conversational AI systems, a critical challenge in training effective multi-turn intent classification models lies in the generation of large-scale, domain-specific, multilingua…
Understanding Fairness-Accuracy Trade-offs in Machine Learning Models: Does Promoting Fairness Undermine Performance?
Junhua Liu, Roy Ka-Wei Lee, Kwan Hui Lim
Fairness in both Machine Learning (ML) predictions and human decision-making is essential, yet both are susceptible to different forms of bias, such as algorithmic and data-driven…