Dan Shi
4 papers · 2024–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(3)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐣
Hot Topic Early Bird
🐝
Cross-Pollinator
(15)
Conferences
AAAI (1)
ACL (1)
EMNLP (1)
NIPS (1)
Top co-authors
Keywords
large language model
(2)
intent classification
(1)
supervised fine-tuning
(1)
mechanistic interpretability
(1)
sparse autoencoder
(1)
steering vector
(1)
integrated gradient
(1)
commonsense reasoning
(1)
dialogue understanding
(1)
parametric knowledge
(1)
knowledge conflict
(1)
concept editing
(1)
context processing
(1)
feature intervention
(1)
knowledge annotation
(1)
neuron editing
(1)
context-aware neuron
(1)
neuron reweighting
(1)
reinforcement learning
(1)
slot identification
(1)
Papers
Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Models
ACL 2026
Towards a Unified Paradigm of Concept Editing in Large Language Models
EMNLP 2025
IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neurons
NIPS 2024
CORECODE: A Common Sense Annotated Dialogue Dataset with Benchmark Tasks for Chinese Large Language Models
AAAI 2024