Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Guowen Xu

Guowen Xu

3 indexed papers

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

Crypto×3NLP×1

Frequent co-authors

Rui Zhang3×
Hongwei Li3×
Zihan Wang2×
Qingchuan Zhao2×
Xinyuan Qian1×
Yu Liu1×

Research Timeline

2026
The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training

The paper investigates how various fine-tuning methods can be used both to intentionally misalign and subsequently realign large language models (LLMs), revealing distinct strengths for attack and defense mechanisms.

Black-Box Skill Stealing Attack from Proprietary LLM Agents: An Empirical Study

This paper presents the first systematic study of black-box skill stealing attacks against proprietary LLM agents, demonstrating that structured agent skills can be easily extracted, posing a significant and often overlooked copyright risk.

FragToken: Amplifying LLM Inference Costs through Noncanonical Token Generation

This paper proposes a method to induce fragmented generation in large language models to increase inference cost without degrading model utility.

Highlighted terms show continued research focus across papers

Papers

cs.CREmpiricalRecentSep 25, 2026

FragToken: Amplifying LLM Inference Costs through Noncanonical Token Generation

Zihan Wang, Rui Zhang, Xinyuan Qian, Qingchuan Zhao +2 more

This paper proposes a method to induce fragmented generation in large language models to increase inference cost without degrading model utility.

View →
cs.CRApr 23, 2026

Black-Box Skill Stealing Attack from Proprietary LLM Agents: An Empirical Study

Zihan Wang, Rui Zhang, Yu Liu, Chi Liu +3 more

This paper presents the first systematic study of black-box skill stealing attacks against proprietary LLM agents, demonstrating that structured agent skills can be easily extracted, posing a signific…

View →
cs.CRcs.CLApr 9, 2026

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

Rui Zhang, Hongwei Li, Yun Shen, Xinyue Shen +5 more

The paper investigates how various fine-tuning methods can be used both to intentionally misalign and subsequently realign large language models (LLMs), revealing distinct strengths for attack and def…

View →