Elamur Research⌕
☰
home / authors / Jian Gang Ngui

Jian Gang Ngui

Jian Gang Ngui has 6 papers in our library, in 2017–2026, most of them on Multilingual & cross-lingual NLP, Bias, fairness & safety, Language models & pretraining; often with Peerat Limkonchotiwat, Wei Qi Leong, Yosephine Susanto.

6 papers in our library · 2017–2026

OpenAlex · h-index 4 · 34 works · 42 citations OpenAlex, 2026-10-14

📄 6 works in our library · 🔗 Cited 220 times in our library · ⭐ Paper Stars ranking: #5330

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

🏛️AI SingaporeSingapore · Singapore2023–2026 · 12 paperscurrent🎓National University of SingaporeSingapore · Singapore2017–2026 · 8 paperscurrent🏢GoogleMountain View · United States2026 · 4 paperscurrent🎓University of ArizonaTucson · United States2021–2023 · 2 papers

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 10The field of science this work belongs to (OpenAlex fields).Computer Science · 5 worksArts and Humanities · 4 worksArtificial Intelligence · 5 worksLanguage and Linguistics · 4 worksSafety Research · 3 worksSocial Sciences · 3 worksComputer Vision and Pattern Recognition · 1 workDevelopmental and Educational Psychology · 1 workExperimental and Cognitive Psychology · 1 workPsychology · 1 work

🧭 Topics 6Research subjects and languages the work is about.Multilingual & cross-lingual NLP · 2 worksLanguage models & pretraining · 1 workBias, fairness & safety · 2 worksEnglish · 1 workEvaluation & benchmarks · 1 workSyntax & grammar formalisms · 1 work

 Works by year

2020s

20262 papers20252 papers20231 paper

2010s

20171 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation (2025 · 182 citations)
    Multilingual LLMs are often evaluated on machine-translated copies of English MMLU. This adds translation artifacts and keeps a US- and Europe-centred knowledge bias that may not matter to speakers of other languages. The authors measure this bias and build an alternative. Around 200 annotators, both paid…
  2. BHASA: A Holistic Southeast Asian Linguistic and Cultural Evaluation Suite for Large Language Models (2023 · 33 citations)
    Most large-scale LLM benchmarks, such as HELM and BIG-bench, focus on English. Southeast Asian (SEA) languages get little systematic evaluation. BHASA addresses this gap with an evaluation suite in three parts:
  3. SEA-LION: Southeast Asian Languages in One Network (2025 · 29 citations)
    Most open LLMs are designed around English and perform poorly on Southeast Asian languages. Lower-resource ones such as Burmese, Lao, Khmer and Filipino are hit hardest, and even regional models like SeaLLMs and Sailor fall short on Thai and Tamil. The AI Singapore team responds with SEA-LION, two instruction-tuned…
  4. SEA-Guard: Culturally Grounded Multilingual Safeguard for Southeast Asia (2026)
    Most safety classifiers that screen LLM inputs and outputs are built for English. Multilingual ones usually depend on machine-translated English data, which serves Southeast Asian languages poorly and misses local cultural, religious and regulatory sensitivities. The authors address this gap with an agentic synthesis…
  5. SEA-SafeguardBench: Culturally Grounded Safety Benchmark for Southeast Asian Languages (2026)
    Safeguard models that screen LLM inputs and outputs for harm are mostly tested in English. Multilingual safety benchmarks usually rely on machine translation, which can distort low-resource languages and miss local cultural risks. Southeast Asia has especially little coverage. SEA-SafeguardBench addresses this gap…
  6. <i>Wh</i>-questions in Singapore English tell us what about questions with declarative syntax? (2017)
    This squib questions a typological claim by Bobaljik & Wurmbrand (2015, "B&W"). B&W argue that no language genuinely combines English-style wh-fronting with Chinese-style wh-in-situ. On their account, apparent optional in-situ questions in fronting languages are questions with declarative syntax (DSQs). Their…

 Co-authors here

12 of 16 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 220 times (of the 149,439 papers whose bibliographies we read); 68 citing papers with a page here →.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/jian-gang-ngui/