Beyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models
Preprint; under submission to NeurIPS 2026, 2026
We study dynamic boundary evaluation for language models, using skill-guided search and difficulty calibration to characterize model capabilities beyond fixed benchmarks and static worst-case attacks.
Recommended citation: Wang, H., Yu, D., & Zhang, H. (2026). "Beyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models." Preprint; under submission.
