🧑‍🔬 Ruochen Xu

🏛️ Affiliations

🏛️Ministry of Education of the People's Republic of ChinaBeijing · China2026 · 5 paperscurrent🏢MicrosoftRedmond · United States2020–2023 · 24 papers🎓Carnegie Mellon UniversityPittsburgh · United States2016–2020 · 9 papers🔬State Key Laboratory of Silicon MaterialsHangzhou2017–2019 · 9 papers🎓Zhejiang UniversityHangzhou · China2017–2019 · 9 papers🔬Huaneng Clean Energy Research InstituteBeijing · China2022–2025 · 8 papers🎓Huazhong University of Science and TechnologyWuhan · China2023–2025 · 3 papers🎓Zhengzhou UniversityZhengzhou · China2024 · 2 papers🎓University of Maryland, College ParkCollege Park · United States2018–2019 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 7 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.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. G-Eval: NLG Evaluation using Gpt-4 with Better Human Alignment (2023 · 2,000 citations)
   Automatically evaluating the quality of texts generated by NLG systems is difficult. Classical metrics such as BLEU and ROUGE correlate poorly with human judgments and also require reference texts. The authors, from Microsoft Azure AI, propose G-Eval, an approach in which a large language model evaluates text without…
2. Enhancing Factual Consistency of Abstractive Summarization (2021 · 190 citations)
   Abstractive summarizers often produce text that misstates or invents facts from the source. Prior work estimates that up to 30% of such outputs contain these errors, which undermines trust in them. The authors address this in two ways. First, FASum is a transformer encoder-decoder summarizer that builds a per-article…
3. SciAgent: Tool-augmented Language Models for Scientific Reasoning (2024 · 55 citations)
   Even strong LLMs often fail at STEM problems because they need both mathematical skill and specialised domain knowledge.
4. Dynamic Evaluation of Large Language Models by Meta Probing Agents (2024 · 30 citations)
   Static public benchmarks can leak into LLM training data, so reported scores may overstate what models can actually do.

All works

13 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

1. G-Eval: NLG Evaluation using Gpt-4 with Better Human AlignmentConference on Empirical Methods in Natural Language Processing (EMNLP)Yang Liu, Dan Iter, Yichong Xu, et al.2023 · 2,000 citations
2. Enhancing Factual Consistency of Abstractive SummarizationConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Chenguang Zhu, William Hinthorn, Ruochen Xu, et al.2021 · 190 citations
3. A Hierarchical Network for Abstractive Meeting Summarization with Cross-Domain Pretraining ↗Findings of the Association for Computational Linguistics: EMNLP 2020 · no summary yetChenguang Zhu et al.2020 · 182 citations
4. Unsupervised Cross-lingual Transfer of Word Embedding Spaces ↗Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · no summary yetRuochen Xu et al.2018 · 150 citations
5. Cross-lingual Distillation for Text Classification ↗Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetRuochen Xu, Yiming Yang2017 · 87 citations
6. Fusing Context Into Knowledge Graph for Commonsense Question Answering ↗Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 · no summary yetYichong Xu et al.2021 · 86 citations
7. Predicting Performance for Natural Language Processing Tasks ↗Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · no summary yetMengzhou Xia et al.2020 · 79 citations
8. SciAgent: Tool-augmented Language Models for Scientific ReasoningConference on Empirical Methods in Natural Language Processing (EMNLP)Yubo Ma, Zhibin Gou, Junheng Hao, et al.2024 · 55 citations
9. Formality Style Transfer with Hybrid Textual Annotations ↗arXiv:1903.06353 · no summary yetRuochen Xu, Tao Ge, Furu Wei2019 · 54 citations
10. Cross-lingual Alignment vs Joint Training: A Comparative Study and A Simple Unified Framework ↗arXiv (Cornell University) · no summary yetZi-Rui Wang et al.2019 · 52 citations
11. Dynamic Evaluation of Large Language Models by Meta Probing AgentsarXiv:2402.14865Kaijie Zhu, Jindong Wang, Qinlin Zhao, et al.2024 · 30 citations
12. The ARIEL-CMU Systems for LoReHLT18 ↗arXiv (Cornell University) · no summary yetAditi Chaudhary et al.2019 · 6 citations
13. ParaTag: A Dataset of Paraphrase Tagging for Fine-Grained Labels, NLG Evaluation, and Data Augmentation ↗Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · no summary yetShuohang Wang et al.2022 · 5 citations

🤝 Co-authors here

12 of 18 co-authors with a page, the most papers together first.

• Chenguang Zhu ×2
• Shuohang Wang ×2
• Aixin Sun
• Dan Iter
• Jindong Wang
• Kaijie Zhu
• Liangming Pan
• Meng Jiang
• Michael Zeng
• Qingkai Zeng
• Xing Xie
• Xuedong Huang

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Conference on Empirical Methods in Natural Language Processing (EMNLP) ×4: EMNLP 2024, EMNLP 2023
• Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics ×2
• Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): NAACL 2021
• Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021
• Findings of the Association for Computational Linguistics: EMNLP 2020

🔗 Cited by

Papers of our library cite their works 1,507 times (of the 149,439 papers whose bibliographies we read); 249 citing papers with a page here →.

Updated 30 October 2026

↑ back to top

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