Mingzhe Du

Mingzhe Du has 3 papers in our library, in 2025–2026, most of them on Language models & pretraining, Evaluation & benchmarks, Reasoning; often with Anh Tuan Luu, Liangming Pan, Rui Mao.

3 papers in our library · 2025–2026

The profile is the library's match of the name; two people with one name are not always told apart.

Affiliations

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

Of its works in our library, with the number of works on each.

The most cited first (OpenAlex and our library).

AntiLeakBench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge (2025 · 12 citations)
Large language models are usually tested on public, static benchmarks, and those test items can leak into the training data of later models, which inflates their scores.
NUS-IDS at AMIYA/VarDial 2026: Improving Arabic Dialectness in LLMs with Reinforcement Learning (2026 · 2 citations)
The paper addresses a known weakness of current LLMs: when asked for Dialectal Arabic (DA), they tend to answer in Modern Standard Arabic (MSA).
SeCuRepair: Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair Framework (2026 · 1 citation)
SeCuRepair targets automated vulnerability repair (AVR) for C/C++ functions. The authors argue that supervised fine-tuning (SFT) teaches models to copy one reference patch. Valid fixes that are written differently get penalised, so models latch onto surface cues such as variable names. Their alternative is a…

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

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

Papers of our library cite their works 12 times (of the 149,439 papers whose bibliographies we read); 2 citing papers with a page here →.

Updated 1 November 2026