Lattice AI Research

Research focus

Red-Teaming & Adversarial Robustness (2)Constitutional AI & AI Ethics (1)RLHF & Preference Learning (1)Eval Frameworks & Benchmarks (1)

Frequent co-authors

Michael Backes (2)Rui Zhang (1)Hongwei Li (1)Yun Shen (1)

Papers (2)

Apr 9, 2026

Tsinghua AI3w ago

The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training

LLM safety is a cat-and-mouse game: ORPO excels at breaking alignment, while DPO is best at restoring it, but at the cost of overall usefulness.

Rui Zhang, Hongwei Li, Yun Shen +6

Constitutional AI & AI Ethics Red-Teaming & Adversarial Robustness RLHF & Preference Learning

Mar 2, 2026

Real Money, Fake Models: Deceptive Model Claims in Shadow APIs

Shadow APIs promising access to top LLMs like GPT-5 and Gemini 2.5 often deliver significantly degraded performance (down to 47.21% accuracy) and fail identity verification, casting doubt on research relying on them.

Yage Zhang, Yukun Jiang, Yukun Jiang +4

Eval Frameworks & Benchmarks Natural Language Processing Open-Source Models & Weights+1

Xinyue Shen

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)

Search

Xinyue Shen

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)