1 citations · 2 across the 11 of their papers we have counts for
7 papers · 1 filter
MAIGO: Mitigating Lost-in-Conversation with History-Cleaned On-Policy Self-Distillation
Haoyu Zheng, Yun Zhu, Shu Yuan +5
Large language models often solve tasks from a fully specified prompt but degrade when the same requirements unfold over multiple turns, known as the lost-in-conversation (LiC) gap…
Jailbreaking with Universal Multi-Prompts
Yu-Ling Hsu, Hsuan Su, Shang-Tse Chen
Large language models (LLMs) have seen rapid development in recent years, revolutionizing various applications and significantly enhancing convenience and productivity. However, al…
Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging
Hua Farn, Hsuan Su, Shachi H Kumar +3
Fine-tuning large language models (LLMs) for downstream tasks often leads to catastrophic forgetting, notably degrading the safety of originally aligned models. While some existing…
Step by Step to Fairness: Attributing Societal Bias in Task-oriented Dialogue Systems
Hsuan Su, Rebecca Qian, Chinnadhurai Sankar +4
Recent works have shown considerable improvements in task-oriented dialogue (TOD) systems by utilizing pretrained large language models (LLMs) in an end-to-end manner. However, the…
Learning from Red Teaming: Gender Bias Provocation and Mitigation in Large Language Models
Hsuan Su, Cheng-Chu Cheng, Hua Farn +4
Recently, researchers have made considerable improvements in dialogue systems with the progress of large language models (LLMs) such as ChatGPT and GPT-4. These LLM-based chatbots…
Position Matters! Empirical Study of Order Effect in Knowledge-grounded Dialogue
Hsuan Su, Shachi H Kumar, Sahisnu Mazumder +7
With the power of large pretrained language models, various research works have integrated knowledge into dialogue systems. The traditional techniques treat knowledge as part of th…
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…