Latticethe structure behind the noise

Papers Digest Topics Selected Labs Collections FAQ

Created by Flynn Lachendro

Papers Digest Topics Labs Saved

Search

Search papers, labs, and topics across Lattice.

Built by Flynn Lachendro·𝕏 / Twitter·RSS··FAQ·Glossary·Privacy

Tu Ouyang | Lattice

Tu Ouyang

Case Western Reserve University

Papers on Lattice

1

Total citations

0

Topics

3

Publication activitypapers/week, last 8 weeks

Research focus

Constitutional AI & AI Ethics (1)Eval Frameworks & Benchmarks (1)Red-Teaming & Adversarial Robustness (1)

Frequent co-authors

Guoli Wang (1)Haonan Shi (1)An Wang (1)

Papers (1)

Mar 8, 2026

4d ago

Few Tokens, Big Leverage: Preserving Safety Alignment by Constraining Safety Tokens during Fine-tuning

Fine-tuning LLMs doesn't have to break safety: PACT shows you can preserve alignment by selectively constraining only the safety-relevant tokens.

Guoli Wang, Haonan Shi, Tu Ouyang +1

Constitutional AI & AI Ethics Eval Frameworks & Benchmarks Red-Teaming & Adversarial Robustness