Elamur Research⌕
☰
home / authors / Samuel Cahyawijaya

Samuel Cahyawijaya

Samuel Cahyawijaya works in natural language processing, with a focus on how language technology is measured and how well it serves languages beyond English. The two papers here, from 2020 and 2023, both build evaluation resources. One gathers scattered datasets into a standard benchmark for a language with little prior infrastructure. The other designs reproducible tests for a conversational large language model. The work touches Evaluation & benchmarks, Multilingual & cross-lingual NLP, Reasoning and Vision & language.

The earlier paper, IndoNLU (2020), responded to Indonesian datasets that were fragmented and hard to reproduce. It collected twelve existing datasets of formal and informal text, gave them fixed splits, and grouped them into four task families. It also introduced Indo4B, a cleaned pre-training corpus. The more recent and more widely cited paper, A Multitask, Multilingual, Multimodal Evaluation of ChatGPT (2023), turned to large language models. It tested a December 2022 version of ChatGPT in a zero-shot setting on 23 public datasets spanning eight task types, including translation, summarization, question answering and misinformation detection. It also examined multilingual coverage, reasoning, hallucination, and visual ability elicited through code generation.

Cahyawijaya is currently affiliated with the Hong Kong University of Science and Technology, where most of the bylines fall from 2020 onward, and also with AI Singapore. Earlier papers list the Bandung Institute of Technology, and 2025 bylines include Cohere. Co-authors on the papers here include Bryan Wilie, who appears on both, along with Pascale Fung, Yejin Bang and Genta Indra Winata.

Samuel Cahyawijaya has 5 papers in our library, in 2020–2024, most of them on Multilingual & cross-lingual NLP, Language models & pretraining, Evaluation & benchmarks; often with Genta Indra Winata, Pascale Fung, Alham Fikri Aji.

5 papers in our library · 2020–2024

OpenAlex · h-index 25 · 118 works · 3,804 citations OpenAlex, 2026-10-14

📄 5 works in our library · 🔗 Cited 1,142 times in our library · 9 more in our library without a page yet · ⭐ Paper Stars ranking: #1680

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

🎓Hong Kong University of Science and TechnologyHong Kong · China2020–2025 · 98 paperscurrent🏛️AI SingaporeSingapore · Singapore2024–2025 · 2 paperscurrent🎓Pelita Harapan UniversityTangerang · Indonesia2025 · 1 papercurrent🏢CohereSan Francisco · United States2025–2026 · 14 papers🎓Bandung Institute of TechnologyBandung · Indonesia2014–2018 · 3 papers🎓Korea Advanced Institute of Science and TechnologyDaejeon · South Korea2022–2023 · 2 papers🎓Kumamoto UniversityKumamoto · Japan2022–2023 · 2 papers🎓University of TasmaniaHobart · Australia2023 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 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 5The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 5 worksComputer Science · 5 worksArtificial Intelligence · 5 worksLanguage and Linguistics · 5 worksComputer Vision and Pattern Recognition · 1 work

🧭 Topics 8Research subjects and languages the work is about.Evaluation & benchmarks · 2 worksMultilingual & cross-lingual NLP · 3 worksLanguage models & pretraining · 2 worksReasoning · 1 workVision & language · 1 workSentiment & emotion · 1 workGrammatical error correction & learner language · 1 workLow-resource languages · 1 work

 Works by year

2020s

20241 paperSamuel Cahyawijaya's papers of 202420233 papersSamuel Cahyawijaya's papers of 202320201 paperSamuel Cahyawijaya's papers of 2020

 Papers

The most cited first (OpenAlex and our library).

  1. A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity (2023 · 876 citations)
    When ChatGPT appeared, its abilities were known mostly from anecdotes, and OpenAI had released no benchmark numbers.
  2. IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding (2020 · 265 citations)
    Indonesian has a very large online user base, but NLP work on it has advanced slowly. Datasets are scattered and poorly documented, and many studies omit code or test splits, so results cannot be reproduced. The authors respond with IndoNLU, the first Indonesian NLU benchmark. It gathers twelve existing datasets…
  3. NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages (2023 · 130 citations)
    Most of Indonesia's 700+ languages have almost no public NLP datasets or benchmarks, even when they have millions of speakers.
  4. LLMs Are Few-Shot In-Context Low-Resource Language Learners (2024 · 92 citations)
    Large language models handle low-resource languages poorly, and adapting them through fine-tuning or adapters is expensive and can cause catastrophic forgetting.
  5. Multilingual Large Language Models Are Not (Yet) Code-Switchers (2023 · 85 citations)
    Code-switching (CSW), where speakers alternate between languages within a single utterance, is common in multilingual communities.

All works

14 works of theirs in our library, the most cited first; 5 with a page here, the others link their original until we summarise them.

  1. A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and InteractivityarXiv:2302.04023Yejin Bang, Samuel Cahyawijaya, Nayeon Lee, et al.2023 · 876 citations
  2. IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language UnderstandingConference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL)Bryan Wilie, Karissa Vincentio, Genta Indra Winata, et al.2020 · 265 citations
  3. NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local LanguagesConference of the European Chapter of the Association for Computational Linguistics (EACL)Genta Indra Winata, Alham Fikri Aji, Samuel Cahyawijaya, et al.2023 · 130 citations
  4. LLMs Are Few-Shot In-Context Low-Resource Language LearnersConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Samuel Cahyawijaya, Holy Lovenia, Pascale Fung2024 · 92 citations
  5. CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark ↗arXiv:2406.05967 · no summary yetDavid Romero et al.2024 · 87 citations
  6. Multilingual Large Language Models Are Not (Yet) Code-SwitchersConference on Empirical Methods in Natural Language Processing (EMNLP)Ruochen Zhang, Samuel Cahyawijaya, Jan Christian Blaise Cruz, et al.2023 · 85 citations
  7. SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages ↗Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing · no summary yetHoly Lovenia et al.2024 · 54 citations
  8. LLM Internal States Reveal Hallucination Risk Faced With a Query ↗arXiv:2407.03282 · no summary yetZiwei Ji et al.2024 · 51 citations
  9. Prompting Multilingual Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languages ↗arXiv:2303.13592 · no summary yetZheng-Xin Yong et al.2023 · 48 citations
  10. WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines ↗Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) · no summary yetGenta Indra Winata et al.2025 · 45 citations
  11. InstructAlign: High-and-Low Resource Language Alignment via Continual Crosslingual Instruction Tuning ↗arXiv:2305.13627 · no summary yetSamuel Cahyawijaya et al.2023 · 22 citations
  12. High-Dimensional Interlingual Representations of Large Language Models ↗Proceedings of the 7th Workshop on Research in Computational Linguistic Typology and Multilingual NLP · no summary yetBryan Wilie et al.2025 · 4 citations
  13. Lost in Simulation: LLM-Simulated Users are Unreliable Proxies for Human Users in Agentic Evaluations ↗Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetPreethi Seshadri et al.2026 · 2 citations
  14. ITLC at SemEval-2026 Task 11: Normalization and Deterministic Parsing for Formal Reasoning in LLMs ↗Proceedings of the 20th International Workshop on Semantic Evaluation (2026) · no summary yetWicaksono Leksono Muhamad et al.2026 · 1 citation

 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 1,142 times (of the 141,840 papers whose bibliographies we read); 125 citing papers with a page here →.

Updated

↑ back to top

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