Papers by Weikai Lu

2 papers
SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic Embeddings (2025.acl-long)

Copied to clipboard

Challenge: Existing low-resource security alignment methods struggle with the security risks posed by additional modalities.
Approach: They propose to use multimodal datasets to enhance safety alignment but it is costly to construct these datasets.
Outcome: Experiments on image, video, and audio-based MLLMs show that the proposed method can synthesize a high-quality embedding on a single RTX3090 GPU within 24 seconds.
SDD: Self-Degraded Defense against Malicious Fine-tuning (2025.acl-long)

Copied to clipboard

Challenge: Open-source Large Language Models (LLMs) employ safety alignment methods to resist harmful instructions, but malicious fine-tuning can easily bypass these safeguards.
Approach: They propose a framework to prevent malicious fine-tuning of large language models on harmful data by using alignment methods that encourage them to produce irrelevant responses to harmful prompts.
Outcome: The proposed framework reduces the general capability of the LLM when malicious fine-tuning fails, rendering it incapable of following harmful instructions.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations