Lijun Li

Assessment of Multimodal Large Language Models in Alignment with Human Values

2024 · arXiv (Cornell University)

Large Language Models (LLMs) aim to serve as versatile assistants aligned with human values, as defined by the principles of being helpful, honest, and harmless (hhh). However, in terms of Multimodal Large Language Models (MLLMs), …

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment

2025 · arXiv (Cornell University)

With rapid advancement and increasing accessibility of LLMs, fine-tuning aligned models has become a critical step for adapting them to real-world applications, which makes the safety of this fine-tuning process more important than ever. However, …