6 papers
SocialPersona: Benchmarking Personalized Profiling and Response with Multimodal Social-Media Context
Qinkai Zhang, Yanyan Zhao, Xin Lu +3
Personalized language-model assistants are often evaluated through a memory lens: can a model recall preferences users have explicitly stated in dialogue? More comprehensive person…
Self-Foveate: Enhancing Diversity and Difficulty of Synthesized Instructions from Unsupervised Text via Multi-Level Foveation
Mingzhe Li, Xin Lu, Yanyan Zhao
Synthesizing high-quality instruction data from unsupervised text is a promising paradigm for training large language models (LLMs), yet automated methods for this task still exhib…
STAR-S: Improving Safety Alignment through Self-Taught Reasoning on Safety Rules
Di Wu, Yanyan Zhao, Xin Lu +2
Defending against jailbreak attacks is crucial for the safe deployment of Large Language Models (LLMs). Recent research has attempted to improve safety by training models to reason…
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…
How Does Sequence Modeling Architecture Influence Base Capabilities of Pre-trained Language Models? Exploring Key Architecture Design Principles to Avoid Base Capabilities Degradation
Xin Lu, Yanyan Zhao, Si Wei +3
Pre-trained language models represented by the Transformer have been proven to possess strong base capabilities, and the representative self-attention mechanism in the Transformer…
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…