5 papers · 1 filter
Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring
Honglin Mu, Han He, Yuxin Zhou +9
Large language model (LLM) safety is a critical issue, with numerous studies employing red team testing to enhance model security. Among these, jailbreak methods explore potential…
Can Large Language Models Understand You Better? An MBTI Personality Detection Dataset Aligned with Population Traits
Bohan Li, Jiannan Guan, Longxu Dou +12
The Myers-Briggs Type Indicator (MBTI) is one of the most influential personality theories reflecting individual differences in thinking, feeling, and behaving. MBTI personality de…
Concise and Precise Context Compression for Tool-Using Language Models
Yang Xu, Yunlong Feng, Honglin Mu +9
Through reading the documentation in the context, tool-using language models can dynamically extend their capability using external tools. The cost is that we have to input lengthy…
Improving Language Model Reasoning with Self-motivated Learning
Yunlong Feng, Yang Xu, Libo Qin +2
Large-scale high-quality training data is important for improving the performance of models. After trained with data that has rationales (reasoning steps), models gain reasoning ca…
Beyond Static Evaluation: A Dynamic Approach to Assessing AI Assistants' API Invocation Capabilities
Honglin Mu, Yang Xu, Yunlong Feng +4
With the rise of Large Language Models (LLMs), AI assistants' ability to utilize tools, especially through API calls, has advanced notably. This progress has necessitated more accu…