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

Zihan Zhang

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

ML×1NLP×1Crypto×1AI×1

Frequent co-authors

Dongjie Fu1×
Di Cao1×
Xize Cheng1×
Wenxu Jia1×
Yifu Chen1×
Shengpeng Ji1×

Research Timeline

2026
When Alignment Isn't Enough: Response-Path Attacks on LLM Agents

This paper introduces the Relay Tampering Attack (RTA), demonstrating that malicious third-party relays can undermine the security of LLM agents by modifying responses post-alignment, even if the LLM itself is perfectly aligned.

CultureForest: Understanding and Evaluating Cultural Norm Grounded Reasoning in LLMs

The paper introduces CultureForest, a new benchmark for evaluating Cultural Norm Grounded Reasoning in LLMs, demonstrating that models struggle to apply their cultural knowledge effectively in realistic, open-ended scenarios.

X$^3$-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment

This paper proposes X$^3$-OPD, a framework for transferring reasoning capabilities from text-based models to audio-language models using on-policy distillation.

Highlighted terms show continued research focus across papers

Papers

cs.LGEmpiricalRecentJul 23, 2026

X$^3$-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment

Dongjie Fu, Di Cao, Xize Cheng, Zihan Zhang +5 more

This paper proposes X$^3$-OPD, a framework for transferring reasoning capabilities from text-based models to audio-language models using on-policy distillation.

View →
cs.CLRecentJun 1, 2026

CultureForest: Understanding and Evaluating Cultural Norm Grounded Reasoning in LLMs

Yangfan Ye, Xiaocheng Feng, Jialong Tang, Xiayu Cao +4 more

The paper introduces CultureForest, a new benchmark for evaluating Cultural Norm Grounded Reasoning in LLMs, demonstrating that models struggle to apply their cultural knowledge effectively in realist…

View →
cs.CRcs.AIRecentMay 4, 2026

When Alignment Isn't Enough: Response-Path Attacks on LLM Agents

Mingyu Luo, Zihan Zhang, Zesen Liu, Yuchong Xie +6 more

This paper introduces the Relay Tampering Attack (RTA), demonstrating that malicious third-party relays can undermine the security of LLM agents by modifying responses post-alignment, even if the LLM…

View →