Elamur Research⌕
☰
home / authors / Shikun Zhang

Shikun Zhang

Shikun Zhang has 6 papers in our library, in 2023–2026, most of them on Language models & pretraining, Bias, fairness & safety, Reasoning; often with Wei Ye, Yutao Mou, Yuxiao Luo.

6 papers in our library · 2023–2026

OpenAlex · h-index 2 · 12 works · 12 citations OpenAlex, 2026-10-14

📄 6 works in our library · 🔗 Cited 186 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #5551

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

🎓Peking UniversityBeijing · China2009–2026 · 11 paperscurrent

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 8The field of science this work belongs to (OpenAlex fields).Computer Science · 6 worksArtificial Intelligence · 6 worksArts and Humanities · 5 worksLanguage and Linguistics · 5 worksSafety Research · 2 worksSocial Sciences · 2 worksComputer Vision and Pattern Recognition · 1 workInformation Systems · 1 work

🧭 Topics 6Research subjects and languages the work is about.Language models & pretraining · 4 worksEvaluation & benchmarks · 1 workBias, fairness & safety · 3 worksInformation retrieval & search · 1 workReasoning · 2 worksEfficient models & compression · 1 work

💡 Concepts 1Key ideas and methods explained on our concept pages.Latent semantic indexing · 1 work

 Works by year

2020s

20264 papers20251 paper20231 paper

 Papers

The most cited first (OpenAlex and our library).

  1. PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization (2023 · 194 citations)
    Teams that instruction-tune open LLMs usually reuse Alpaca's hyperparameters, partly because comparing tuned variants is hard.
  2. SaRO: Enhancing LLM Safety through Reasoning-based Alignment (2025 · 11 citations)
    Safety-tuned LLMs tend to fail in two opposite ways. Unfamiliar jailbreak prompts can still trick them, yet they also refuse harmless requests that only look risky. The authors find that, in embedding space, jailbreak or harmful prompts often lie close to ordinary ones. They argue that models should reason explicitly…
  3. Retrieval as Generation: A Unified Framework with Self-Triggered Information Planning (2026 · 8 citations)
    Typical RAG pipelines fetch documents once, using the initial query, and then generate from that fixed context.
  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.
  5. LeLoRA: Learnable Low-Rank Adaptation of Large Language Models (2026)
    LoRA-style fine-tuning usually relies on hand-set, fixed choices about which parts of each weight matrix to train, such as a uniform rank or always the principal or minor singular directions.
  6. Thinking Twice Makes Large Language Models Safer and More Helpful (2026)
    Safety alignment of LLMs usually trades usefulness for harmlessness: stronger safety tends to bring more false refusals and lower utility.

All works

7 works of theirs in our library, the most cited first; 6 with a page here, the others link their original until we summarise them.

  1. PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning OptimizationarXiv:2306.05087Yidong Wang, Zhuohao Yu, Zhengran Zeng, et al.2023 · 194 citations
  2. SaRO: Enhancing LLM Safety through Reasoning-based AlignmentarXiv:2504.09420Yutao Mou, Yuxiao Luo, Shikun Zhang, et al.2025 · 11 citations
  3. Retrieval as Generation: A Unified Framework with Self-Triggered Information PlanningAnnual Meeting of the Association for Computational Linguistics (ACL)Bo Li, Mingda Wang, Gexiang Fang, et al.2026 · 8 citations
  4. ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and FeedbackFindings of the Association for Computational LinguisticsYutao Mou, Zhangchi Xue, Lijun Li, et al.2026 · 3 citations
  5. LeLoRA: Learnable Low-Rank Adaptation of Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Xiaoling Zhou, Mingjie Zhang, Zhemg Lee, et al.2026
  6. Thinking Twice Makes Large Language Models Safer and More HelpfulFindings of the Association for Computational LinguisticsYutao Mou, Yuxiao Luo, Shikun Zhang, et al.2026
  7. Joint Optimization of Training Data and Policy in RLHF ↗Findings of the Association for Computational Linguistics: ACL 2026 · no summary yetZhuohao Yu et al.2026

 Co-authors here

12 of 14 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 186 times (of the 149,439 papers whose bibliographies we read); 50 citing papers with a page here →.

Updated

↑ back to top

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