Weilong Dong

5 papers · 2023–2025 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13) 🐣 Hot Topic Early Bird ❓ The Questioner

Venues

EMNLP (2) ACL (1) COLING (1) NeurIPS (1)

Top co-authors

Deyi Xiong (5) Xinwei Wu (5) Shaoyang Xu (3) Renren Jin (2) Junzhuo Li (1) Minghui Xu (1) Dan Shi (1) Shuangzhi Wu (1) Chao Bian (1) Tianhao Shen (1)

Research topics

Artificial Intelligence (5) Core AI (5) Machine Learning (3) Natural Language Processing (3) Resources & Methods (3) Application Areas (2) Deep Learning (1) Security & Privacy (1) Core Methods (1) Models (1) Privacy (1)

Keywords

large language model (3) value alignment (2) neuron editing (2) model editing (2) privacy neuron (2) integrated gradient (2) privacy protection (1) pre-trained language model (1) privacy leakage (1) multilingual natural language processing (1) parametric knowledge (1) knowledge conflict (1) activation patching (1) context processing (1) concept vector (1) memorization capability (1) activation value (1) context-aware neuron (1) model compression (1) neuron reweighting (1)

Papers

CONTRANS: Weak-to-Strong Alignment Engineering via Concept Transplantation COLING 2025 Exploring Multilingual Concepts of Human Values in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages? EMNLP 2024 IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neurons NeurIPS 2024 Mitigating Privacy Seesaw in Large Language Models: Augmented Privacy Neuron Editing via Activation Patching ACL 2024 DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models EMNLP 2023