EMNLP, the Conference on Empirical Methods in Natural Language Processing, is a premier international academic conference in the field of natural language processing. Organized by SIGDAT, the Special Interest Group on Linguistic Data of the Association for Computational Linguistics (ACL), the conference is held annually and covers a wide range of topics, including machine translation, information extraction, text generation and sentiment analysis. In 2026, the conference was held from October 24 to 29 in Budapest, the capital of Hungary. A total of 20 papers by faculty and students of the School of Artificial Intelligence, Jilin University have been accepted by the conference.
1. Mitigating LLM Over-Refusal via Dynamic Semantic Routing Calibration
First author: Zixuan Wang (Master's student, 2024 cohort)
Corresponding author: Dandan Guo
2. Bayesian Sparse Low-Rank Adaptation for Large Language Model Uncertainty Estimation
First author: Jijie Zhang (Master's student, 2025 cohort)
Corresponding authors: Quan Zhang, Dandan Guo
3. MetaGen: Self-Evolving Roles and Topologies for Multi-Agent LLM Reasoning
First authors: Yimeng Wang (Master's student, 2024 cohort), Jiaxing Zhao (Master's student, 2025 cohort)
Corresponding author: Xuan Song
4. FIVER: Adaptive Fusion of Formal and Informal Verification for Mathematical Reasoning in LLMs
First authors: Yujie Li, Ao Xu (PhD student, 2024 cohort)
Corresponding author: Tieru Wu
5. SAIGuard: Communication-State Simulation for Proactive Defense of LLM Multi-Agent Systems
First author: Ruxue Shi (Master's student, 2024 cohort)
Corresponding author: Xin Wang
6. OCR-MetaReasoning Benchmark: Evaluating the Meta-Reasoning Ability of MLLMs in Text-Rich Image Understanding
First author: Gengxu Li (PhD student, 2025 cohort)
Corresponding author: Yuan Wu
7. VCIFBench: Evaluating Complex Instruction Following for Video Understanding
First author: Huangchen Xu (Undergraduate student, 2024 cohort)
Corresponding author: Yuan Wu
8. From Isolation to Alignment: Unified LoRA for Efficient Multi-Task Learning
First author: Jinda Liu (Undergraduate student, 2022 cohort)
Corresponding author: Yuan Wu
9. How Robust is OCR-Reasoning? Evaluating OCR-Reasoning Robustness of Vision-Language Models under Visual Perturbations
First author: Yuxing Cheng (PhD student, 2026 cohort)
Corresponding authors: Yuan Wu, Yi Chang
10. MMPCBench: Benchmarking Multimodal Large Language Models on Proactive Critique of Flawed Inputs
First author: Jinzhe Li (PhD student, 2025 cohort)
Corresponding authors: Yuan Wu, Yi Chang
11. Beyond Blind Compliance: Benchmarking Task Verification in OCR Reasoning
First author: Yue Zhou (PhD student, 2024 cohort)
Corresponding author: Yuan Wu
12. Counterfactual Self-Distillation: A Distribution-Shaping Framework for Entity-Fact Unlearning in Large Language Models
First author: Ying Zhao (PhD student, 2022 cohort)
Corresponding authors: Wei Wang, Yuan Tian, Yi Chang
13. RecToolBench: Benchmarking Recommendation-Specific Tool Orchestration under Fuzzy User Intent
Authors: Xiao Chen, Yicheng Zhao, Yingying Wu, Zhendong Chu, Changyi Ma*, Qingsong Wen, Xuan Song
14. When Graphs Whisper: Graph Structure Serialization for Embedding Alignment in Cold-Start Recommendation
Authors: Yujing Zhang, Huachi Zhou, Ruochen Liu, Qinggang Zhang*, Luyao Zhuang, Hao Chen, Zijin Hong, Chang Yang, Xiao Huang
15. CulturalMenuBench: Probing the Knowledge-Application Gap in Multimodal Culinary Reasoning
Authors: Bo Zeng, Linfeng Gao, Peiqin Lin, Yu Zhao, Mingyan Zeng, Yu Tong, Xintong Wang, Linlong Xu, Longyue Wang, Weihua Luo, Qinggang Zhang*, Jinsong Su
16. How Much Can We Trust LLM Search Agents? Measuring Endorsement Vulnerability to Web Content Manipulation
Authors: Yimeng Chen, Zhe Ren, Firas Laakom, Yu Li, Dandan Guo, Jürgen Schmidhuber
17. The Geometry of Safety Drifts: Step-level Refusal-Subspace Monitoring for Reasoning Large Language Models
Authors: Liming Lu, Anan Du, Fanzhen Liu, Hechang Chen, Shuchao Pang
18. Evaluating LLMs on Conversational Text-to-SQL under Chain Ambiguity and Intent Drift
Authors: Yujia Liu, Jiayan Lin, Zijin Hong, Zheng Yuan, Shengyuan Chen, Hao Chen, Qinggang Zhang, Xiao Huang, Feiran Huang
19. SAIGuard: Communication-State Simulation for Proactive Defense of LLM Multi-Agent Systems
Authors: Ruxue Shi, Yili Wang, Mengnan Du, Qinggang Zhang, Rui Miao, Yixin Liu, Xin Wang
20. SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization
Authors: Jingyi He, Haiyan Zhao, Ruxue Shi, Yanguang Liu, Xin Wang, Fei Sun, Mengnan Du
