Peng Fu
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
This paper theoretically analyzes Continuous Adversarial Training (CAT) for LLMs using In-context Learning (ICL) theory, proving that embedding space perturbations effectively enhance robustness against token-space jailbreaks and proposing a singular value regularization method for improvement.
The paper introduces DocFormBench, a new benchmark for content-aware document formatting, and proposes DocFormFlow, a workflow that improves formatting accuracy and efficiency by decoupling target localization from modification execution.
Papers
What to Format and How: A Benchmark and Workflow Approach for Document Formatting
Shihao Rao, Liang Li, Jiapeng Liu, Tong Lin +5 more
The paper introduces DocFormBench, a new benchmark for content-aware document formatting, and proposes DocFormFlow, a workflow that improves formatting accuracy and efficiency by decoupling target loc…