Elamur Research⌕
☰
home / authors / Xiaogeng Liu

Xiaogeng Liu

Xiaogeng Liu has 3 papers in our library, in 2023–2025, most of them on Bias, fairness & safety, Language models & pretraining; often with Chaowei Xiao, Muhao Chen, Hao Li.

3 papers in our library · 2023–2025

OpenAlex · ORCID · h-index 10 · 43 works · 385 citations OpenAlex, 2026-10-14

📄 3 works in our library · 🔗 Cited 446 times in our library · 2 more in our library without a page yet · ⭐ Paper Stars ranking: #4435

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓University of Wisconsin–MadisonMadison · United States2023–2025 · 5 paperscurrent🎓Johns Hopkins UniversityBaltimore · United States2025 · 1 paperEmploymentcurrent🎓Nanjing University of Finance and EconomicsNanjing · China2006–2021 · 10 papers🎓Huazhong University of Science and TechnologyWuhan · China2021–2023 · 5 papers🎓South China Agricultural UniversityGuangzhou · China2019–2020 · 3 papers

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.

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 3 worksArts and Humanities · 3 worksComputer Science · 3 worksLanguage and Linguistics · 3 worksSafety Research · 1 workSocial Sciences · 1 work

🧭 Topics 2Research subjects and languages the work is about.Bias, fairness & safety · 2 worksLanguage models & pretraining · 1 work

 Works by year

2020s

20252 papers20231 paper

 Papers

The most cited first (OpenAlex and our library).

  1. AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models (2023 · 350 citations)
    Jailbreak attacks push safety-aligned LLMs into answering requests they should refuse. Earlier approaches fall into two camps. Hand-written prompts, such as the "Do-Anything-Now (DAN)" family, scale poorly and lose effectiveness as models are updated. Gradient-guided token search, such as GCG, produces gibberish…
  2. AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection (2025 · 20 citations)
    LLM-based agents that run shell commands, browse websites or query databases can cause harm in two ways. Task-specific risks break rules that an administrator sets for a given job, such as access restrictions on medical records. Systemic risks threaten confidentiality, integrity or availability, for example through…
  3. PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free (2025 · 16 citations)
    Lightweight prompt guard classifiers screen LLM inputs for prompt injection, but they often learn a shortcut.

All works

5 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. AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language ModelsarXiv:2310.04451Xiaogeng Liu, Nan Xu, Muhao Chen, et al.2023 · 350 citations
  2. JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks ↗arXiv:2404.03027 · no summary yetWeidi Luo et al.2024 · 66 citations
  3. MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding ↗arXiv (Cornell University) · no summary yetFei Wang et al.2024 · 48 citations
  4. AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety DetectionAnnual Meeting of the Association for Computational Linguistics (ACL)Weidi Luo, Shenghong Dai, Xiaogeng Liu, et al.2025 · 20 citations
  5. PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for FreeAnnual Meeting of the Association for Computational Linguistics (ACL)Hao Li, Xiaogeng Liu, Ning Zhang, et al.2025 · 16 citations

 Co-authors here

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

Venues

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

 Cited by

Papers of our library cite their works 446 times (of the 149,439 papers whose bibliographies we read); 113 citing papers with a page here →.

Updated

↑ back to top

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