Elamur Research⌕
☰
home / authors / Lijun Li

Lijun Li

Lijun Li has 4 papers in our library, in 2024–2026, most of them on Bias, fairness & safety, Language models & pretraining, Evaluation & benchmarks; often with Jing Shao, Dahua Lin, Hao Li.

4 papers in our library · 2024–2026

OpenAlex · ORCID · h-index 11 · 81 works · 382 citations OpenAlex, 2026-10-14

📄 4 works in our library · 🔗 Cited 102 times in our library · ⭐ Paper Stars ranking: #7265

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

🏢Alibaba GroupHangzhou · China2023–2026 · 3 paperscurrent🎓Taiyuan University of Science and TechnologyTaiyuan · China2013–2026 · 3 paperscurrent🏥Beijing Tian Tan HospitalBeijing · China2026 · 1 papercurrent🎓Capital Medical UniversityBeijing · China2026 · 1 papercurrent🎓Shanghai Jiao Tong UniversityShanghai · China2026 · 1 papercurrent🎓Huazhong University of Science and TechnologyWuhan · China2003–2009 · 17 papers🎓Beihang UniversityBeijing · China2014–2019 · 8 papers🎓Liaoning Shihua UniversityFushun · China2009–2011 · 5 papers🔬State Key Laboratory of Virtual Reality Technology and SystemsBeijing2016–2019 · 4 papers🎓Changsha University of Science and TechnologyChangsha · China2008–2011 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 24 more institutions 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 · 4 worksComputer Science · 4 worksArts and Humanities · 2 worksLanguage and Linguistics · 2 worksSafety Research · 1 workSocial Sciences · 1 work

🧭 Topics 3Research subjects and languages the work is about.Bias, fairness & safety · 4 worksLanguage models & pretraining · 2 worksEvaluation & benchmarks · 1 work

 Works by year

2020s

20261 paper20252 papers20241 paper

 Papers

The most cited first (OpenAlex and our library).

  1. SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models (2024 · 119 citations)
    Existing LLM safety benchmarks have several weaknesses. They cover narrow slices of harm, and modern models now handle their questions almost perfectly. Many also need slow human grading or costly GPT grading, and few can assess both models and attack/defense techniques. SALAD-Bench addresses these gaps with a…
  2. Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment (2025 · 11 citations)
    Fine-tuning a safety-aligned LLM can weaken its refusal behaviour even when the training data look harmless.
  3. Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context Injection (2025 · 6 citations)
    The paper argues that most image-based jailbreaks of multimodal LLMs use the picture as a trigger. They paint harmful text onto it, add adversarial noise, or generate a loosely related image, but the visual content rarely defines a coherent scenario. The authors introduce a vision-centric jailbreak setting, where the…
  4. ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback (2026 · 3 citations)
    LLM agents that call external tools can be steered into harmful actions, either by malicious users or by prompt injections hidden in tool outputs.

 Co-authors here

11 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 102 times (of the 149,439 papers whose bibliographies we read); 31 citing papers with a page here →.

Updated

↑ back to top

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