5 papers · 1 filter
MoGU: A Framework for Enhancing Safety of Open-Sourced LLMs While Preserving Their Usability
Yanrui Du, Sendong Zhao, Danyang Zhao +6
Large Language Models (LLMs) are increasingly deployed in various applications. As their usage grows, concerns regarding their safety are rising, especially in maintaining harmless…
From Artificially Real to Real: Leveraging Pseudo Data from Large Language Models for Low-Resource Molecule Discovery
Yuhan Chen, Nuwa Xi, Yanrui Du +4
Molecule discovery serves as a cornerstone in numerous scientific domains, fueling the development of new materials and innovative drug designs. Recent developments of in-silico mo…
AS-ES Learning: Towards Efficient CoT Learning in Small Models
Nuwa Xi, Yuhan Chen, Sendong Zhao +3
Chain-of-Thought (CoT) serves as a critical emerging ability in LLMs, especially when it comes to logical reasoning. Attempts have been made to induce such ability in small models…
Analyzing the Inherent Response Tendency of LLMs: Real-World Instructions-Driven Jailbreak
Yanrui Du, Sendong Zhao, Ming Ma +2
Extensive work has been devoted to improving the safety mechanism of Large Language Models (LLMs). However, LLMs still tend to generate harmful responses when faced with malicious…
Don't Ignore Dual Logic Ability of LLMs while Privatizing: A Data-Intensive Analysis in Medical Domain
Yanrui Du, Sendong Zhao, Muzhen Cai +4
Extensive studies have been devoted to privatizing general-domain Large Language Models (LLMs) as Domain-Specific LLMs via feeding specific-domain data. However, these privatizatio…