Get started
Author

Haonan Shi

Observed name: Shi, Haonan
Observed institution: Case Western Reserve University
ORCID: 0009-0006-1445-9156
Observed ORCID: 0009-0006-1445-9156
OpenAlex ID: A5125733190
Few Tokens, Big Leverage: Preserving Safety Alignment by Constraining Safety Tokens during Fine-tuning
2026 · Guoli Wang, Haonan Shi, et al. · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)
EASE: Practical and Efficient Safety Alignment for Small Language Models
2026 · Association for Artificial Intelligence 2026, Ouyang, Tu, et al. · Underline Science Inc.
1065 - EASE: Practical and Efficient Safety Alignment for Small Language Models
2026 · Association for Artificial Intelligence 2026, Ouyang, Tu, et al. · Underline Science Inc.
Beyond Token Positions: Safety Alignment Across Denoising Steps in Diffusion Language Models
2026 · Guoli Wang, Haonan Shi, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Works count: 4
Citation count:
H-index:
I10-index:
Year
Topic
Type