8 papers
SinoGlyphBench: A Diagnostic Benchmark for Chinese Glyph-Level Obfuscation in Language-Model Moderation
Yifan Wang, Zimu Wang, Suliu Qin +10
Glyph-level obfuscation can leave harmful Chinese content readable to humans while degrading automated moderation. We introduce SinoGlyphBench, a diagnostic benchmark that identifi…
You Never Know a Person, You Only Know Their Defenses: Detecting Levels of Psychological Defense Mechanisms in Supportive Conversations
Hongbin Na, Zimu Wang, Zhaoming Chen +9
Psychological defenses are strategies, often automatic, that people use to manage distress. Rigid or overuse of defenses is negatively linked to mental health and shapes what speak…
FinDebate: Multi-Agent Collaborative Intelligence for Financial Analysis
Tianshi Cai, Guanxu Li, Nijia Han +10
We introduce FinDebate, a multi-agent framework for financial analysis, integrating collaborative debate with domain-specific Retrieval-Augmented Generation (RAG). Five specialized…
Benchmarking and Improving LVLMs on Event Extraction from Multimedia Documents
Fuyu Xing, Zimu Wang, Wei Wang +1
The proliferation of multimedia content necessitates the development of effective Multimedia Event Extraction (M2E2) systems. Though Large Vision-Language Models (LVLMs) have shown…
Following the TRACE: A Structured Path to Empathetic Response Generation with Multi-Agent Models
Ziqi Liu, Ziyang Zhou, Yilin Li +2
Empathetic response generation is a crucial task for creating more human-like and supportive conversational agents. However, existing methods face a core trade-off between the anal…
Lost in Pronunciation: Detecting Chinese Offensive Language Disguised by Phonetic Cloaking Replacement
Haotan Guo, Jianfei He, Jiayuan Ma +8
Phonetic Cloaking Replacement (PCR), defined as the deliberate use of homophonic or near-homophonic variants to hide toxic intent, has become a major obstacle to Chinese content mo…
Domain-specific Guided Summarization for Mental Health Posts
Lu Qian, Yuqi Wang, Zimu Wang +4
In domain-specific contexts, particularly mental health, abstractive summarization requires advanced techniques adept at handling specialized content to generate domain-relevant an…
Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models
Lu Yu, Haiyang Zhang, Changsheng Xu
Due to the impressive zero-shot capabilities, pre-trained vision-language models (e.g. CLIP), have attracted widespread attention and adoption across various domains. Nonetheless,…