Congnan Liu
Congnan Liu has 2 papers in our library, in 2024–2025, most of them on Language models & pretraining, Multilingual & cross-lingual NLP, Code & programming languages; often with Ge Zhang, Jiaheng Liu, Ken Deng.
OpenAlex · h-index 1 · 4 works · 2 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 Cited 21 times in our library · ⭐ Paper Stars ranking: #8432
Fields, topics and concepts
📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksLanguage and Linguistics · 2 worksInformation Systems · 1 work
🧭 Topics 3Research subjects and languages the work is about.Language models & pretraining · 1 workCode & programming languages · 1 workMultilingual & cross-lingual NLP · 1 work
Works by year
2020s
Papers
- DDK: Distilling Domain Knowledge for Efficient Large Language Models (2024 · 23 citations)
Smaller LLMs are cheaper to deploy, and knowledge distillation from a stronger model can improve them. However, existing LLM distillation methods train on a fixed data mix. They overlook that the gap between student and teacher differs widely by domain. For example, a Qwen-1.5 1.8B student trails its 14B teacher far… - M2RC-EVAL: Massively Multilingual Repository-level Code Completion Evaluation (2025 · 8 citations)
Benchmarks for repository-level code completion usually cover fewer than five programming languages and report only one averaged score.
Co-authors here
- Ge Zhang ×2
- Jiaheng Liu ×2
- Ken Deng ×2
- Yanan Wu ×2
- Chenchen Zhang
- Haoran Que
- He Zhu
- Jian Yang
- Jie Liu
- Jin Ke
- Jinyang Guo
- Linzheng Chai
Venues
- Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2025
- Conference on Neural Information Processing Systems (NeurIPS): NeurIPS 2024
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/congnan-liu/