Elamur Research⌕
☰
home / authors / Haiyue Song

Haiyue Song

Haiyue Song has 2 papers in our library, in 2023–2025, most of them on Language models & pretraining, Information extraction, Multilingual & cross-lingual NLP; often with Ahmed Elshabrawy, Alham Fikri Aji, Fei Cheng.

2 papers in our library · 2023–2025

OpenAlex · ORCID · Wikidata · h-index 5 · 35 works · 271 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 179 citations in our library · 3 more in our library without a page yet · ⭐ Paper Star rank #3664

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

🔬National Institute of Information and Communications TechnologyTokyo · Japan2019–2026 · 9 papersEmployment 2019–2023Employment 2023–2026current🎓Kyoto UniversityKyoto · Japan2018–2024 · 19 papersEducation 2018–2020Education 2020–2024Employment 2020–2021🎓Shanghai Jiao Tong UniversityShanghai · China2014–2020 · 4 papersEducation 2014–2018🏢Preferred Networks, Inc.Chiyoda City · Japan2026Employment since 2026🏢Line CorporationTokyo · Japan2019Employment 2019🎓Nagoya UniversityNagoya · Japan2017–2018Education 2017–2018

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.

 Topics

 Language models & pretraining (1) Information extraction (1) Multilingual & cross-lingual NLP (1) Semitic languages (1)

 Works by year

2020s

20251 paper20231 paper

 Papers

The most cited first (OpenAlex and our library).

  1. GPT-RE: In-context Learning for Relation Extraction using Large Language Models (2023 · 252 citations)
    Large language models such as GPT-3 do well on many tasks through in-context learning (ICL), but on relation extraction (RE) they have trailed fine-tuned models like BERT-based PURE.
  2. When Alignment Hurts: Decoupling Representational Spaces in Multilingual Models (2025 · 1 citation)
    The paper questions a common belief: that a low-resource variety always gains when a model aligns it tightly with a related high-resource standard.

Also in our library

3 more works of theirs are in our library without a page here yet; they will appear as we publish them.

 Co-authors here

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

 Cited by

Papers of our library cite their works 179 times (of the 140,884 papers whose bibliographies we read); 11 citing papers with a page here →.

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