EMNLP (The Conference on Empirical Methods in Natural Language Processing) is one of the premier international conferences in natural language processing, covering research directions including machine translation, text generation, text classification, information extraction, question answering systems and language models. In 2025, the conference will be held from November 5 to 9 in Suzhou, China. A total of 11 papers by faculty and students of the School of Artificial Intelligence, Jilin University have been accepted by the conference.
1. R-LoRA: Randomized Multi-Head LoRA for Efficient Multi-task Learning
First author: Jinda Liu (Undergraduate student, 2022 cohort)
Corresponding author: Yuan Wu
2. LoRA-MGPO: Mitigating Double Descent in LoRA Fine-Tuning via Momentum-Guided Perturbation Optimization
First author: Yupeng Chang (PhD student, 2023 cohort)
Corresponding author: Yuan Wu
3. Don't Take the Premise for Granted: Evaluating the Premise Critique Ability of Large Language Models
Co-first authors: Jinzhe Li (PhD student, 2025 cohort), Gengxu Li (PhD student, 2025 cohort)
Corresponding authors: Yi Chang, Yuan Wu
4. Large Language Model Evaluation via Matrix Nuclear-Norm
First author: Yahan Li (Master's student, 2023 cohort)
Corresponding author: Yuan Wu
5. NLoRA: Nyström-Initiated Low-Rank Adaptation for Large Language Models
First author: Chenlu Guo (Master's student, 2023 cohort)
Corresponding author: Yuan Wu
6. Rethinking Data Selection at Scale: Random Selection is Almost All You Need
First author: Tingyu Xia (PhD student, 2021 cohort)
Corresponding authors: Yuan Wu, Bowen Yu, Yi Chang
7. Detoxifying Large Language Models via the Diversity of Toxic Samples
First author: Ying Zhao (PhD student, 2022 cohort)
Corresponding authors: Wei Wang, Yuan Tian, Yi Chang
8. APLOT: Robust Reward Modeling via Adaptive Preference Learning with Optimal Transport
First author: Zhuo Li (PhD student, 2021 cohort)
Corresponding authors: Dandan Guo, Xiang Wan
9. MicroEdit: Neuron-level Knowledge Disentanglement and Localization in Lifelong Model Editing
First author: Shiqi Wang (PhD student, 2023 cohort)
Corresponding author: Qi Wang
10. CrystalICL: Enabling In-Context Learning for Crystal Generation
First author: Ruobing Wang (PhD student, 2025 cohort)
Corresponding author: Xin Wang
11. Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems
First author: Xu Shen (Master's student, 2023 cohort)
Corresponding author: Xin Wang
