4 papers
Thinking vs. NoThinking: Towards Interpreting Reasoning Mechanisms of Large Language Models via Sparse Autoencoders
Bo Cheng, Qiaolin Lu, Yi Chang +1
While Large Language Models (LLMs) employing Chain-of-Thought (CoT) exhibit superior reasoning capabilities, the neural mechanisms distinguishing this explicit Thinking mode from d…
MeTA-LoRA: Data-Efficient Multi-Task Fine-Tuning for Large Language Models
Bo Cheng, Xu Wang, Jinda Liu +2
Low-Rank Adaptation (LoRA) has emerged as one of the most widely used parameter-efficient fine-tuning (PEFT) methods for adapting large language models (LLMs) to downstream tasks.…
Align, Don't Divide: Revisiting the LoRA Architecture in Multi-Task Learning
Jinda Liu, Bo Cheng, Yi Chang +1
Parameter-Efficient Fine-Tuning (PEFT) is essential for adapting Large Language Models (LLMs). In practice, LLMs are often required to handle a diverse set of tasks from multiple d…
CGMatch: A Different Perspective of Semi-supervised Learning
Bo Cheng, Jueqing Lu, Yuan Tian +3
Semi-supervised learning (SSL) has garnered significant attention due to its ability to leverage limited labeled data and a large amount of unlabeled data to improve model generali…