Yihuai Hong
6 papers · 2024–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot (3) π Renaissance Researcher (5) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (17) π§ Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
EMNLP (4)
AAAI (1)
ACL (1)
Top co-authors
Keywords
large language model
(2)
knowledge erasure
(2)
machine unlearning
(2)
knowledge editing
(2)
natural language understanding
(1)
efficient inference
(1)
model editing
(1)
model interpretability
(1)
language model
(1)
feed-forward network
(1)
policy network
(1)
knowledge removal
(1)
inference acceleration
(1)
concept erasure
(1)
residual stream
(1)
feature analysis
(1)
parameter inspection
(1)
parametric knowledge
(1)
activation patching
(1)
cross entropy loss
(1)
Papers
The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction
ACL 2025
Precise In-Parameter Concept Erasure in Large Language Models
EMNLP 2025
Intrinsic Test of Unlearning Using Parametric Knowledge Traces
EMNLP 2025
ConsistentEE: A Consistent and Hardness-Guided Early Exiting Method for Accelerating Language Models Inference
AAAI 2024
Interpretability-based Tailored Knowledge Editing in Transformers
EMNLP 2024
Dissecting Fine-Tuning Unlearning in Large Language Models
EMNLP 2024