1 citations · 1 across the 4 of their papers we have counts for
6 papers
A Broader Look at Model Merging: Rethinking Implicit Regularization Induced by Task Arithmetic
Sin-Han Yang, Shih-Cheng Huang, Chieh-Yen Lin +3
Model merging aims to build a multi-task model cheaply by combining the weights of individual task-specific models. To perform well across multiple tasks, most existing merging met…
Transfer: Coefficient Transfer for Efficient Model Merging
Shih-Cheng Huang, Zhi Rui Tam, Chieh-Yen Lin +3
Model merging offers a promising solution for combining multiple fine-tuned checkpoints into a single model through parameter arithmetic. However, finding optimal merging coefficie…
Adaptive Helpfulness-Harmlessness Alignment with Preference Vectors
Ren-Wei Liang, Chin-Ting Hsu, Chan-Hung Yu +6
Ensuring that large language models (LLMs) are both helpful and harmless is a critical challenge, as overly strict constraints can lead to excessive refusals, while permissive mode…
Chat Vector: A Simple Approach to Equip LLMs with Instruction Following and Model Alignment in New Languages
Shih-Cheng Huang, Pin-Zu Li, Yu-Chi Hsu +5
Recently, the development of open-source large language models (LLMs) has advanced rapidly. Nevertheless, due to data constraints, the capabilities of most open-source LLMs are pri…
Systematic Analysis for Pretrained Language Model Priming for Parameter-Efficient Fine-tuning
Shih-Cheng Huang, Shih-Heng Wang, Min-Han Shih +2
Parameter-efficient (PE) methods (like Prompts or Adapters) for adapting pre-trained language models (PLM) to downstream tasks have been popular recently. However, hindrances still…
Learning to Generate Prompts for Dialogue Generation through Reinforcement Learning
Hsuan Su, Pohan Chi, Shih-Cheng Huang +4
Much literature has shown that prompt-based learning is an efficient method to make use of the large pre-trained language model. Recent works also exhibit the possibility of steeri…