Elamur Research⌕
☰
home / authors / Xiangyu Zhao

Xiangyu Zhao

Xiangyu Zhao has 6 papers in our library, in 2022–2026, most of them on Language models & pretraining, Reasoning, Bias, fairness & safety; often with Maolin Wang, Pengyue Jia, Jingyu Peng.

6 papers in our library · 2022–2026

OpenAlex · ORCID · h-index 10 · 54 works · 516 citations OpenAlex, 2026-10-14

📄 6 works in our library · 🔗 Cited 113 times in our library · ⭐ Paper Stars ranking: #4192

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

🎓City University of Hong KongHong Kong · China2024–2026 · 8 paperscurrent🎓Hong Kong Polytechnic UniversityHong Kong · China2026 · 2 paperscurrent🎓Beihang UniversityBeijing · China2016–2017 · 8 papers🎓University of Electronic Science and Technology of ChinaChengdu · China2019–2025 · 7 papers🎓Tianjin UniversityTianjin · China2019–2022 · 4 papers🎓Southwest Jiaotong UniversityChengdu · China2024–2025 · 2 papers🎓Tsinghua UniversityBeijing · China2021–2025 · 2 papers🎓Zhejiang UniversityHangzhou · China2009 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 9 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 11The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 6 worksComputer Science · 6 worksArtificial Intelligence · 6 worksLanguage and Linguistics · 6 worksHealth Informatics · 1 workMedicine · 1 workSafety Research · 1 workSocial Sciences · 1 workDevelopmental and Educational Psychology · 1 workInformation Systems · 1 workPsychology · 1 work

🧭 Topics 6Research subjects and languages the work is about.Language models & pretraining · 5 worksInformation extraction · 1 workBias, fairness & safety · 2 worksReasoning · 2 worksEnglish · 1 workGrammatical error correction & learner language · 1 work

💡 Concepts 1Key ideas and methods explained on our concept pages.Information extraction · 1 work

 Works by year

2020s

20263 papers20251 paper20231 paper20221 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Large Language Models for Generative Information Extraction: A Survey (2023 · 406 citations)
    Information extraction (IE) turns raw text into structured knowledge such as entities, relations and events.
  2. Stepwise Reasoning Disruption Attack of LLMs (2025 · 10 citations)
    LLMs are often accessed through third-party platforms and APIs. This means an intermediary could quietly tamper with a model's reasoning while the output still looks normal. The authors study this risk for multi-step reasoning, where one flawed early step can spread through the whole chain. Earlier reasoning attacks…
  3. Logic Jailbreak: Efficiently Unlocking LLM Safety Restrictions Through Formal Logical Expression (2026 · 8 citations)
    The paper asks why safety-aligned LLMs still give in to jailbreaks. The authors propose that alignment learns refusal mostly from surface token patterns, so a harmful request with the same meaning but an unfamiliar form can slip past safeguards. To test this, they present LogiBreak, a black-box attack that rewrites a…
  4. PsychEthicsBench: Evaluating Large Language Models Against Australian Mental Health Ethics (2026 · 2 citations)
    Most safety evaluations of LLMs judge a model by whether it refuses harmful requests. In mental health this is a weak measure. A curt refusal can seem cold, discourage someone from seeking help, or still contain ethically problematic content. Existing medical-ethics benchmarks also tend to assume one shared standard…
  5. MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search (2026 · 1 citation)
    Agentic (deep) search lets an LLM alternate between reasoning and retrieval. Each round adds thinking traces and retrieved passages, so the context grows and key evidence gets buried. The authors call this memory dilution. Existing fixes that summarize, filter or prune memory often miss the shifting intent of…
  6. SC-Ques: A Sentence Completion Question Dataset for English as a Second Language Learners (2022 · 1 citation)
    Sentence completion (SC) items give a sentence with one or more gaps and three to five candidate fillers. They are a staple of English as a Second Language (ESL) exams. Existing public SC collections, such as the MSR SC dataset, hold only a few thousand items and use a fixed gap and option format. That makes them too…

 Co-authors here

12 of 26 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 113 times (of the 149,439 papers whose bibliographies we read); 19 citing papers with a page here →.

Updated

↑ back to top

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