5 papers
Off-Distribution Voices: Fanfiction Subgenres as Universal Vernacular Jailbreaks for Aligned LLMs
Zhongze Luo, Ruihe Shi, Zhenshuai Yin +3
Existing jailbreaks against aligned LLMs are discrete artifacts whose surface forms are easy to fingerprint and patch. We argue that the real failure mode is not any specific promp…
KG2QA: Knowledge Graph-enhanced Retrieval-augmented Generation for Communication Standards Question Answering
Zhongze Luo, Weixuan Wan, Tianya Zhang +2
The rapid evolution of communication technologies has led to an explosion of standards, rendering traditional expert-dependent consultation methods inefficient and slow. To address…
Multi-Physics: A Comprehensive Benchmark for Multimodal LLMs Reasoning on Chinese Multi-Subject Physics Problems
Zhongze Luo, Zhenshuai Yin, Yongxin Guo +3
While multimodal LLMs (MLLMs) demonstrate remarkable reasoning progress, their application in specialized scientific domains like physics reveals significant gaps in current evalua…
ForPKG: A Framework for Constructing Forestry Policy Knowledge Graph and Application Analysis
Jingyun Sun, Zhongze Luo
A policy knowledge graph can provide decision support for tasks such as project compliance, policy analysis, and intelligent question answering, and can also serve as an external k…
LawLuo: A Multi-Agent Collaborative Framework for Multi-Round Chinese Legal Consultation
Jingyun Sun, Chengxiao Dai, Zhongze Luo +2
Legal Large Language Models (LLMs) have shown promise in providing legal consultations to non-experts. However, most existing Chinese legal consultation models are based on single-…