39 citations · 71 across the 22 of their papers we have counts for
8 papers · 1 filter
Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models
Di Wu, Xin Lu, Yanyan Zhao +1
Although large language models (LLMs) achieve effective safety alignment at the time of release, they still face various safety challenges. A key issue is that fine-tuning often co…
RKLD: Reverse KL-Divergence-based Knowledge Distillation for Unlearning Personal Information in Large Language Models
Bichen Wang, Yuzhe Zi, Yixin Sun +2
With the passage of the Right to Be Forgotten (RTBF) regulations and the scaling up of language model training datasets, research on model unlearning in large language models (LLMs…
Large Language Models Meet Text-Centric Multimodal Sentiment Analysis: A Survey
Hao Yang, Yanyan Zhao, Yang Wu +6
Compared to traditional sentiment analysis, which only considers text, multimodal sentiment analysis needs to consider emotional signals from multimodal sources simultaneously and…
Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patching
Weixiang Zhao, Yulin Hu, Zhuojun Li +7
Safety alignment of large language models (LLMs) has been gaining increasing attention. However, current safety-aligned LLMs suffer from the fragile and imbalanced safety mechanism…
How does Architecture Influence the Base Capabilities of Pre-trained Language Models? A Case Study Based on FFN-Wider and MoE Transformers
Xin Lu, Yanyan Zhao, Bing Qin +3
Pre-trained language models have been proven to possess strong base capabilities, which not only excel in in-distribution language modeling but also show powerful abilities in out-…
Improving the Downstream Performance of Mixture-of-Experts Transformers via Weak Vanilla Transformers
Xin Lu, Yanyan Zhao, Bing Qin +1
Recently, Mixture of Experts (MoE) Transformers have garnered increasing attention due to their advantages in model capacity and computational efficiency. However, studies have ind…
Both Matter: Enhancing the Emotional Intelligence of Large Language Models without Compromising the General Intelligence
Weixiang Zhao, Zhuojun Li, Shilong Wang +5
Emotional Intelligence (EI), consisting of emotion perception, emotion cognition and emotion expression, plays the critical roles in improving user interaction experience for the c…
SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Models
Weixiang Zhao, Shilong Wang, Yulin Hu +6
The continual learning (CL) ability is vital for deploying large language models (LLMs) in the dynamic world. Existing methods devise the learning module to acquire task-specific k…