🧑‍🔬 Zhenliang Zhang

🏛️ Affiliations

🏛️Beijing Institute for General Artificial IntelligenceBeijing · China2023–2026 · 12 paperscurrent🔬Xinjiang Academy of Agricultural and Reclamation ScienceShihezi · China2025–2026 · 6 paperscurrent🎓Peking UniversityBeijing · China2020–2026 · 2 paperscurrent🎓Beijing Institute of TechnologyBeijing · China2015–2023 · 23 papers🎓Colorado State UniversityFort Collins · United States2011–2016 · 13 papers🎓Kunming University of Science and TechnologyKunming · China2004–2010 · 8 papers🎓Zhejiang University of TechnologyHangzhou · China2022–2024 · 7 papers🎓Zhejiang UniversityHangzhou · China2013–2025 · 4 papers🏢TencentShenzhen · China2020 · 4 papers🏛️Jiangsu Academy of Agricultural SciencesNanjing · China2014–2025 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 20 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.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Reasoning with Exploration: An Entropy Perspective (2025 · 63 citations)
   RL training of LLMs with verifiable rewards tends to over-exploit. Models settle into narrow strategies, and reasoning gains level off. The authors ask whether token-level entropy, a classic exploration signal in RL, can identify exploratory reasoning. They analyse Qwen2.5-Base-7B on math problems and find that…
2. ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs (2025 · 14 citations)
   Hallucination detectors that read an LLM's hidden states are appealing because they need no reference answers or repeated sampling.
3. JointCQ: Improving Factual Hallucination Detection with Joint Claim and Query Generation (2026)
   The paper targets factual hallucination detection in open-domain question answering. Retrieval-based checking pipelines usually split an answer into claims, write search queries, gather evidence and then verify each claim. The authors argue that the first two steps are weak: claims lose their context, and queries are…

🤝 Co-authors here

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

• Huixuan Zhang ×2
• Xiaojun Wan ×2
• Bo Dai
• Daixuan Cheng
• Fan Xu
• Furu Wei
• Jiahao Wang
• Junzhe Zhang
• Shaohan Huang
• Wayne Xin Zhao
• Xinyu Hu
• Xuekai Zhu

Venues

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

• Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2025
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026

🔗 Cited by

Papers of our library cite their works 72 times (of the 149,439 papers whose bibliographies we read); 25 citing papers with a page here →.

Updated 2 November 2026

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