🧑‍🔬 Shulin Cao

🏛️ Affiliations

🎓North China University of TechnologyBeijing · China2025–2026 · 2 paperscurrent🎓Tsinghua UniversityBeijing · China2018–2024 · 29 papers🏛️Jiangsu Academy of Agricultural SciencesNanjing · China2009–2025 · 24 papersEmployment since 2018 · Institute of Plant Protection🔬Beijing National Research Center for Information Science and TechnologyBeijing · China2020–2023 · 8 papers🏢Zhipu AIBeijing · China2024–2025 · 5 papers🎓Northwest A&F UniversityYangling · China2014–2019 · 5 papers🎓Yangzhou UniversityYangzhou · China2023–2025 · 4 papers🎓Beijing Normal UniversityBeijing · China2017–2018 · 3 papers

🏛️Northwest A and F UniversityYangling · China2007–2017Education 2007–2017 · College of Plant Protection

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.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks (2024 · 135 citations)
   Most long-context benchmarks reward shallow skills. Answers can often be pulled straight from the text, tasks are frequently synthetic, and scoring relies on fragile metrics like F1 or ROUGE. LongBench v2 targets genuine comprehension and reasoning over very long inputs instead. The authors gathered 503 English…
2. SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation (2025 · 52 citations)
   Adaptive retrieval-augmented generation (RAG) aims to query a search engine only when a large language model actually lacks the knowledge it needs.
3. LongReward: Improving Long-context Large Language Models with AI Feedback (2025 · 21 citations)
   Long-context LLMs are usually fine-tuned on question-answer data that other LLMs generate automatically. That data often contains logical slips, invented facts or incomplete answers, and these flaws carry over into the SFT models. Reinforcement learning could correct such behaviour, but there has been no dependable…

All works

6 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

1. OpenKE: An Open Toolkit for Knowledge Embedding ↗Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations · no summary yetXu Han et al.2018 · 387 citations
2. TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph ↗Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · no summary yetJiaxin Shi et al.2021 · 162 citations
3. LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context MultitasksarXiv:2412.15204Yushi Bai, Shangqing Tu, Jiajie Zhang, et al.2024 · 135 citations
4. KQA Pro: A Dataset with Explicit Compositional Programs for Complex Question Answering over Knowledge Base ↗Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetShulin Cao et al.2022 · 135 citations
5. SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented GenerationAnnual Meeting of the Association for Computational Linguistics (ACL)Zijun Yao, Weijian Qi, Liangming Pan, et al.2025 · 52 citations
6. LongReward: Improving Long-context Large Language Models with AI FeedbackAnnual Meeting of the Association for Computational Linguistics (ACL)Jiajie Zhang, Zhongni Hou, Xin Lv, et al.2025 · 21 citations

🤝 Co-authors here

12 of 17 co-authors with a page, the most papers together first.

• Juanzi Li ×3
• Lei Hou ×3
• Jiajie Zhang ×2
• Xin Lv ×2
• Yuxiao Dong ×2
• Hao Peng
• Jiazheng Xu
• Jie Tang
• Liangming Pan
• Ling Feng
• Shangqing Tu
• Xiaozhi Wang

Venues

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

• Annual Meeting of the Association for Computational Linguistics (ACL) ×3: ACL 2025 ×2
• Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
• Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

🔗 Cited by

Papers of our library cite their works 855 times (of the 149,439 papers whose bibliographies we read); 178 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

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