Di Hong

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Constitutional AI & AI Ethics (1)Data Curation & Synthetic Data (1)Red-Teaming & Adversarial Robustness (1)

Frequent co-authors

Zefeng Wu (1)Weiwei Qi (1)Jielong Chen (1)Tianhang Zheng (1)

Papers (1)

Jul 16, 2026

Zefeng Wu +81w ago

DataShield: Uncovering Risky Fine-Tuning Data Across LLMs Through Consensus Subspace Alignment

DataShield reveals that aligning consensus subspaces across multiple LLMs can drastically enhance safety by filtering out risky fine-tuning data more effectively than previous methods.

Zefeng Wu, Weiwei Qi, Jielong Chen +6

Constitutional AI & AI Ethics Data Curation & Synthetic Data Red-Teaming & Adversarial Robustness

Search

Di Hong

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)