Elamur Research⌕
☰
home / authors / Cheng Liu

Cheng Liu

Cheng Liu has 2 papers in our library, in 2025–2026, most of them on Language models & pretraining, Bias, fairness & safety; often with Bang Zhang, Jia Li, Jiaqi Chen.

2 papers in our library · 2025–2026

OpenAlex · ORCID · h-index 31 · 87 works · 3,738 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 22 times in our library · ⭐ Paper Stars ranking: #8685

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

🔬Institut de Ciència de Materials de BarcelonaCerdanyola del Vallès · Spain2022–2026 · 7 paperscurrent🏛️Consejo Superior de Investigaciones CientíficasMadrid · Spain2025–2026 · 2 paperscurrent🎓Central South UniversityChangsha · China2011–2024 · 26 papers🎓Tianjin UniversityTianjin · China2016–2022 · 12 papers🔬State Key Laboratory of Powder MetallurgyChangsha2019–2021 · 10 papers🎓Zhejiang Sci-Tech UniversityHangzhou · China2022–2024 · 6 papers🎓Soochow UniversitySuzhou · China2021–2025 · 4 papers🎓Huaiyin Normal UniversityHuai'an · China2022–2025 · 3 papers🔬Jiangsu Key Laboratory for Chemistry of Low-Dimensional MaterialsHuai'an · China2022–2025 · 3 papers🎓Tsinghua Shenzhen International Graduate SchoolShenzhen · China2017–2020 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 19 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 4The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksArts and Humanities · 2 worksComputer Science · 2 worksLanguage and Linguistics · 2 works

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

 Works by year

2020s

20261 paper20251 paper

 Papers

The most cited first (OpenAlex and our library).

  1. S²R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning (2025 · 26 citations)
    S$^2$R targets a practical gap. Methods that give LLMs o1-style "deep thinking" usually need huge datasets, heavy compute, or distillation from much stronger models, and it is unclear how to help weaker base models reason better. The authors treat reasoning as a sequence of alternating "solve" and "verify" actions.…
  2. TrajGuard: Streaming Hidden-state Trajectory Detection for Decoding-time Jailbreak Defense (2026)
    Most jailbreak defenses judge a prompt, an output, or a single internal state in isolation. This misses how risk builds up while a response is being generated. The authors compare prompt representations with decoding-time hidden states across several models. They find that jailbreak prompts stay mixed in with benign…

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

Updated

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