ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails

1 code implementation • 19 Feb 2025 • Xiaofei Wen, Wenxuan Zhou, Wenjie Jacky Mo, Muhao Chen

Ensuring the safety of large language models (LLMs) is critical as they are deployed in real-world applications.

Computational Efficiency Pass Classification

Rethinking Backdoor Detection Evaluation for Language Models

no code implementations • 31 Aug 2024 • Jun Yan, Wenjie Jacky Mo, Xiang Ren, Robin Jia

Backdoor detection methods aim to detect whether a released model contains a backdoor, so that practitioners can avoid such vulnerabilities.

MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding

1 code implementation • 13 Jun 2024 • Fei Wang, Xingyu Fu, James Y. Huang, Zekun Li, Qin Liu, Xiaogeng Liu, Mingyu Derek Ma, Nan Xu, Wenxuan Zhou, Kai Zhang, Tianyi Lorena Yan, Wenjie Jacky Mo, Hsiang-Hui Liu, Pan Lu, Chunyuan Li, Chaowei Xiao, Kai-Wei Chang, Dan Roth, Sheng Zhang, Hoifung Poon, Muhao Chen

We introduce MuirBench, a comprehensive benchmark that focuses on robust multi-image understanding capabilities of multimodal LLMs.

Multiple-choice Scene Understanding