Elamur Research⌕
☰
home / authors / Shiyu Chang

Shiyu Chang

Shiyu Chang has 5 papers in our library, in 2018–2025, most of them on Language models & pretraining, Evaluation & benchmarks, Reasoning; often with Yang Zhang, Bairu Hou, Mo Yu.

5 papers in our library · 2018–2025

OpenAlex · ORCID · h-index 49 · 225 works · 8,710 citations OpenAlex, 2026-10-14

📄 5 works in our library · 🔗 380 citations in our library · 2 more in our library without a page yet · ⭐ Paper Star rank #2398

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

🎓University of California, Santa BarbaraSanta Barbara · United States2018–2026 · 48 paperscurrent🏥First Hospital of Jilin UniversityChangchun · China2024–2026 · 22 paperscurrent🏢AccentureNew York · United States2026 · 1 papercurrent🏢IBMArmonk · United States2016–2022 · 57 papers🎓University of Illinois Urbana-ChampaignUrbana · United States2010–2017 · 31 papers🎓Massachusetts Institute of TechnologyCambridge · United States2018–2022 · 18 papers🔬IBM Research - Thomas J. Watson Research CenterYorktown Heights · United States2016–2018 · 12 papers🎓Shanxi Medical UniversityTaiyuan · China2022–2025 · 7 papers🎓Jilin UniversityChangchun · China2024–2025 · 5 papersEmployment · The first hospital of jilin university🎓The University of Texas at AustinAustin · United States2021–2023 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 14 more institutions on single bylines are not listed.

 Concepts, shelves and topics

Of its works in our library: the number of works on each and its rating among them.

💡 Concepts 1 Semantic similarity · 1 work

📚 Shelves 5 Arts and Humanities · 5 works Computer Science · 5 works Artificial Intelligence · 5 works Language and Linguistics · 5 works Computer Vision and Pattern Recognition · 1 work

🧭 Topics 3 Evaluation & benchmarks · 1 work Language models & pretraining · 2 works Reasoning · 1 work

 Works by year

2020s

20251 paper20241 paper20221 paper

2010s

20191 paper20181 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Diverse Few-Shot Text Classification with Multiple Metrics (2018 · 291 citations)
    Most few-shot learning research assumes that all tasks are drawn from one large, homogeneous collection, as with Omniglot or ImageNet.
  2. DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings (2022 · 269 citations)
    Unsupervised sentence embedding methods such as SimCSE train an encoder so that two dropout-perturbed copies of a sentence stay close together.
  3. Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control (2019 · 175 citations)
    Selective rationalization trains a generator to highlight a small part of the input text and a predictor that classifies using only that highlighted part. This paper identifies two weaknesses of the cooperative setup.
  4. A Survey on Data Selection for Language Models (2024 · 85 citations)
    Large language models depend on huge web-scale corpora, but using every available document is often wasteful or harmful because text quality varies widely.
  5. ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning (2025 · 64 citations)
    Reasoning models trained to produce long chains of thought often generate redundant, inefficient reasoning, which inflates inference cost.

Also in our library

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

 Co-authors here

12 of 23 co-authors with a page, the most papers together first.

 Cited by

Papers of our library cite their works 380 times (of the 141,840 papers whose bibliographies we read); 25 citing papers with a page here →.

Updated

↑ back to top

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