Automated Safety Benchmarking: A Multi-agent Pipeline for LVLMs
Open Access
- 9 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 16297-16306
Abstract
No abstract availableFunding Information
- New Generation Artificial Intelligence-National Science and Technology Major Project (2025ZD0124104)
- Shanghai Municipal Special Program for Basic Research on General AI Foundation Models (2025SHZDZX025D09)
This publication has 17 references indexed in Scilit:
- Large multimodal models evaluation: a surveyScience China Information Sciences, 2025
- Compressed Feature Quality Assessment: Dataset and Baselines2025
- AIBench: Towards trustworthy evaluation under the 45°lawDisplays, 2025
- Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark2025
- SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Models2025
- AutoBench: Automatic Testbench Generation and Evaluation Using LLMs for HDL Design2024
- A Survey on Evaluation of Large Language ModelsACM Transactions on Intelligent Systems and Technology, 2024
- A survey on large language model based autonomous agentsFrontiers of Computer Science, 2024
- Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement2023
- PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning2023