🧑‍🔬 Xuezhi Cao

🏛️ Affiliations

🏢MeituanBeijing · China2020–2026 · 20 paperscurrent🎓Shanghai Jiao Tong UniversityShanghai · China2012–2026 · 17 papersEducation since 2013 · Ph.D., Apex Data & Knowledge Management Labcurrent

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily (2023 · 85 citations)
   Safety-aligned LLMs can still be manipulated into giving harmful answers through jailbreak prompts. Existing attacks either depend on laborious hand-written templates (e.g., DAN) or on slow gradient search over white-box models (e.g., GCG). GCG produces nonsensical suffixes that are easy to filter and work poorly on…
2. Meeseeks: A Feedback-Driven, Iterative Self-Correction Benchmark evaluating LLMs' Instruction Following Capability (2026 · 1 citation)
   Large language models often fail to satisfy every requirement in prompts that contain many constraints. Meeseeks is a benchmark that measures how far models can improve when they get repeated, targeted feedback. It works in cycles. The tested model answers a prompt, and each constraint is checked automatically. The…
3. SOP-Maze: Evaluating Large Language Models on Complicated Business Standard Operating Procedures (2026)
   Most instruction-following benchmarks do not test whether LLMs can carry out the long, branching standard operating procedures (SOPs) used in real business workflows, where user input is often noisy.

All works

7 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

1. Table Fact Verification with Structure-Aware Transformer ↗Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · no summary yetHongzhi Zhang et al.2020 · 88 citations
2. A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models EasilyarXiv:2311.08268Peng Ding, Jun Kuang, Dan Ma, et al.2023 · 85 citations
3. A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily ↗Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) · no summary yetPeng Ding et al.2024 · 55 citations
4. A Machine Learning Approach to Prevent Malicious Calls over Telephony Networks ↗Proceedings - IEEE Symposium on Security and Privacy/Proceedings of the ... IEEE Symposium on Security and Privacy · no summary yetHuichen Li et al.2018 · 55 citations
5. Combining Factorization Model and Additive Forest for Collaborative Followee Recommendation ↗no summary yetTianqi Chen et al.2012 · 44 citations
6. Meeseeks: A Feedback-Driven, Iterative Self-Correction Benchmark evaluating LLMs' Instruction Following CapabilityFindings of the Association for Computational LinguisticsJiaming Wang, Yunke Zhao, Peng Ding, et al.2026 · 1 citation
7. SOP-Maze: Evaluating Large Language Models on Complicated Business Standard Operating ProceduresFindings of the Association for Computational LinguisticsJiaming Wang, Zhe Tang, Zehao Jin, et al.2026

🤝 Co-authors here

9 co-authors with a page, the most papers together first.

• Peng Ding ×3
• Jiaming Wang ×2
• Jun Kuang ×2
• Xiaoyu Li ×2
• Yilin Jin ×2
• Zhe Tang ×2
• Jiajun Chen
• Shujian Huang
• ZongYu Wang

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Findings of the Association for Computational Linguistics ×3: Findings of the Association for Computational Linguistics 2026 ×2
• Proceedings - IEEE Symposium on Security and Privacy/Proceedings of the ... IEEE Symposium on Security and Privacy
• Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
• Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)

🔗 Cited by

Papers of our library cite their works 116 times (of the 149,439 papers whose bibliographies we read); 29 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/xuezhi-cao/