Xin Gao
Xin Gao has 5 papers in our library, in 2022–2026, most of them on Language models & pretraining, Reasoning, Question answering; often with Conghui He, Honglin Lin, Qizhi Pei.
OpenAlex · ORCID · h-index 14 · 43 works · 571 citations OpenAlex, 2026-10-14
📄 5 works in our library · 🔗 Cited 34 times in our library · ⭐ Paper Stars ranking: #8186
Affiliations
Fields, topics and concepts
📚 Shelves 15The field of science this work belongs to (OpenAlex fields).Computer Science · 5 worksArts and Humanities · 4 worksArtificial Intelligence · 4 worksLanguage and Linguistics · 4 worksComputer Vision and Pattern Recognition · 3 worksMaterials Science · 1 workMaterials Chemistry · 1 workMathematics · 1 workApplied Mathematics · 1 workComputational Theory and Mathematics · 1 workPsychology · 1 workExperimental and Cognitive Psychology · 1 workSignal Processing · 1 workEngineering · 1 workMedia Technology · 1 work
🧭 Topics 5Research subjects and languages the work is about.Reasoning · 2 worksLanguage models & pretraining · 2 worksQuestion answering · 1 workEnglish · 1 workSpeech & spoken language · 1 work
Works by year
2020s
Papers
- ScholarChemQA: Unveiling the Power of Language Models in Chemical Research Question Answering (2024 · 19 citations)
Chemistry has lacked QA benchmarks built from real research. Existing chemical sets such as KGQA rely on templates over a knowledge graph and mostly test basic concepts. The authors address this gap with ScholarChemQA. They mined chemistry papers whose titles are phrased as questions and treated each abstract as the… - MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusion (2025 · 10 citations)
Most data augmentation for mathematical SFT changes one problem at a time, for example by rewording it or adjusting its difficulty. - ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch (2026 · 5 citations)
Open-source vision-language models lag on chart reasoning, mainly because training data is weak. Synthetic charts tend to be simple and repetitive, and automatically generated QA pairs often contain hallucinated or numerically wrong answers. ChartVerse is a code-driven pipeline that builds both charts and reasoning… - Language-specific Effects on Automatic Speech Recognition Errors for World Englishes (2022 · 3 citations)
The paper asks why commercial speech recognition serves some English speakers worse than others. Earlier work mostly reported a single Word Error Rate (WER), and that number cannot show which sounds fail or why. The authors tested Otter, a captioning engine used inside Zoom, on 1,227 readings of the same passage from… - Overview of EvaHan2026: The First International Evaluation of Ancient Chinese OCR and Layout Analysis (2026)
EvaHan2026 is the fifth edition of the EvaHan shared-task series on ancient Chinese, held with LT4HALA 2026 @ LREC 2026.
Co-authors here
- Conghui He ×2
- Honglin Lin ×2
- Qizhi Pei ×2
- Yu Li ×2
- Zhuoshi Pan ×2
- Chang Liu
- Fan Yang
- Haoyang Li
- Jurgen Schmidhuber
- Lijun Wu
- Mingchen Zhuge
- Nicole Holliday
Venues
- Annual Meeting of the Association for Computational Linguistics (ACL) ×2: ACL 2026, ACL 2025
- International Conference on Computational Linguistics (COLING): COLING 2022
- Workshop on Language Technologies for Historical and Ancient Languages @ LREC: Workshop on Language Technologies for Historical and Ancient Languages @ LREC 2026
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/xin-gao/