Elamur Research⌕
☰
home / authors / Zhenghua Wang

Zhenghua Wang

Zhenghua Wang has 5 papers in our library, in 2024–2026, most of them on Language models & pretraining, Information retrieval & search, Bias, fairness & safety; often with Changze Lv, Xiaoqing Zheng, Xuanjing Huang.

5 papers in our library · 2024–2026

OpenAlex · h-index 1 · 3 works · 2 citations OpenAlex, 2026-10-14

📄 5 works in our library · 🔗 Cited 57 times in our library · ⭐ Paper Stars ranking: #6810

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

🎓Fudan UniversityShanghai · China2026 · 2 paperscurrent

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).Computer Science · 5 worksArts and Humanities · 4 worksArtificial Intelligence · 4 worksLanguage and Linguistics · 4 worksInformation Systems · 1 workComputer Vision and Pattern Recognition · 2 works

🧭 Topics 4Research subjects and languages the work is about.Information retrieval & search · 1 workLanguage models & pretraining · 2 worksBias, fairness & safety · 1 workVision & language · 1 work

💡 Concepts 1Key ideas and methods explained on our concept pages.Retrieval-augmented generation · 1 work

 Works by year

2020s

20263 papers20251 paper20241 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Searching for Best Practices in Retrieval-Augmented Generation (2024 · 150 citations)
    Retrieval-augmented generation (RAG) pipelines consist of many stages, and each stage can be built in several ways.
  2. Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective (2025 · 17 citations)
    The paper asks why LLMs that have been through safety alignment can still be jailbroken. It approaches the question through representation engineering. The authors argue that refusals of harmful requests come from particular activation signatures inside the model, which they call "safety patterns". To find them, they…
  3. VIB-Probe: Detecting and Mitigating Hallucinations in Vision-Language Models via Variational Information Bottleneck (2026 · 3 citations)
    Vision-Language Models often describe things that are not actually in the image. Most existing detectors look only at output confidence, such as logit entropy, or rely on external verifiers. VIB-Probe looks inside the model instead. During decoding, it collects the raw per-head attention outputs from every…
  4. Mitigating Hallucinations in VLMs: Enhancing Visual Attention via Head-Wise Perturbation (2026)
    Vision-language models often hallucinate because they lean on the language priors of their LLM backbone instead of the image.
  5. Mitigating Position Bias in Transformers via Layer-Specific Positional Embedding Scaling (2026)
    Long-context LLMs that use RoPE tend to concentrate attention on the start and end of the input. As a result, they underuse content in the middle, a problem known as "lost-in-the-middle." Earlier fixes such as Attention Buckets, MoICE and Ms-PoE mix several RoPE bases or scales. However, they need repeated forward…

 Co-authors here

12 of 15 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 57 times (of the 149,439 papers whose bibliographies we read); 12 citing papers with a page here →.

Updated

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