Ziwen Xu
11 papers · 2024–2026 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Conference Polyglot (3) π Interdisciplinary Bridge π§ Keyword Pioneer π£ Hot Topic Early Bird π Cross-Pollinator (12)
πΊοΈ
Taxonomy Completionist
(19)
β‘
Prolific Year
(6)
Conferences
ACL (6)
EMNLP (3)
NIPS (2)
Top co-authors
Keywords
large language model
(8)
knowledge editing
(5)
model editing
(3)
model safety
(2)
instruction tuning
(1)
language model
(1)
factual knowledge
(1)
toxicity reduction
(1)
controllable generation
(1)
parameter-efficient tuning
(1)
sparse autoencoder
(1)
control signal
(1)
steering vector
(1)
memory mechanism
(1)
computation graph
(1)
adversarial input
(1)
safety benchmark
(1)
knowledge injection
(1)
multimodal large language model
(1)
synthetic datum
(1)
Papers
How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities
ACL 2026
Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics
ACL 2026
Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms
ACL 2025
Automating Steering for Safe Multimodal Large Language Models
EMNLP 2025
EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models
EMNLP 2025
WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models
NIPS 2024
Knowledge Mechanisms in Large Language Models: A Survey and Perspective
EMNLP 2024
Detoxifying Large Language Models via Knowledge Editing
ACL 2024
Knowledge Circuits in Pretrained Transformers
NIPS 2024
EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models
ACL 2024
EasyInstruct: An Easy-to-use Instruction Processing Framework for Large Language Models
ACL 2024