5 papers
Enhancing Vision-Language Model Reliability with Uncertainty-Guided Dropout Decoding
Yixiong Fang, Ziran Yang, Zhaorun Chen +2
Large vision-language models (LVLMs) excel at multimodal tasks but are prone to misinterpreting visual inputs, often resulting in hallucinations and unreliable outputs. We present…
ChemSafetyBench: Benchmarking LLM Safety on Chemistry Domain
Haochen Zhao, Xiangru Tang, Ziran Yang +8
The advancement and extensive application of large language models (LLMs) have been remarkable, including their use in scientific research assistance. However, these models often g…
Evolving Diverse Red-team Language Models in Multi-round Multi-agent Games
Chengdong Ma, Ziran Yang, Hai Ci +4
The primary challenge in deploying Large Language Model (LLM) is ensuring its harmlessness. Red team can identify vulnerabilities by attacking LLM to attain safety. However, curren…
SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset
Josef Dai, Tianle Chen, Xuyao Wang +4
To mitigate the risk of harmful outputs from large vision models (LVMs), we introduce the SafeSora dataset to promote research on aligning text-to-video generation with human value…
Panacea: Pareto Alignment via Preference Adaptation for LLMs
Yifan Zhong, Chengdong Ma, Xiaoyuan Zhang +5
Current methods for large language model alignment typically use scalar human preference labels. However, this convention tends to oversimplify the multi-dimensional and heterogene…