Elamur Research⌕
☰
home / authors / Yutao Mou

Yutao Mou

Yutao Mou has 3 papers in our library, in 2025–2026, most of them on Bias, fairness & safety, Language models & pretraining, Reasoning; often with Shikun Zhang, Wei Ye, Yuxiao Luo.

3 papers in our library · 2025–2026

OpenAlex · ORCID · h-index 7 · 44 works · 111 citations OpenAlex, 2026-10-14

📄 3 works in our library · 🔗 Cited 11 times in our library · ⭐ Paper Stars ranking: #9522

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 · China2024–2026 · 11 paperscurrent🔬Shanghai Artificial Intelligence LaboratoryShanghai · China2026 · 3 paperscurrent🏢TencentShenzhen · China2026 · 2 paperscurrent🎓Beijing University of Posts and TelecommunicationsBeijing · China2020–2025 · 23 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

 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 worksComputer Science · 3 worksArts and Humanities · 2 worksLanguage and Linguistics · 2 worksSafety Research · 2 worksSocial Sciences · 2 works

🧭 Topics 3Research subjects and languages the work is about.Bias, fairness & safety · 3 worksLanguage models & pretraining · 2 worksReasoning · 2 works

 Works by year

2020s

20262 papers20251 paper

 Papers

The most cited first (OpenAlex and our library).

  1. 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…
  2. 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.
  3. 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.

 Co-authors here

6 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 11 times (of the 149,439 papers whose bibliographies we read); 1 citing paper with a page here →.

Updated

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