Baixiang Huang
5 papers · 2024–2026 · 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 ↓
๐
Conference Polyglot ยท Bronze
๐
Interdisciplinary Bridge ยท Bronze
โ
The Questioner
(3)
Top co-authors
Research topics
Keywords
large language model
(2)
model editing
(2)
knowledge editing
(2)
factual knowledge
(1)
authorship attribution
(1)
ai safety
(1)
safety alignment
(1)
information gain
(1)
agent behavior
(1)
shapley value
(1)
llm agent
(1)
linguistic feature
(1)
hallucination correction
(1)
ethical behavior
(1)
harmful information
(1)
bias injection
(1)
misinformation injection
(1)
behavior steering
(1)
reinforcement learning
(1)
interactive medical questioning
(1)
Papers
Can Editing LLMs Inject Harm?
AAAI 2026
Model Editing as a Double-Edged Sword: Steering Agent Behavior Toward Beneficence or Harm
AAAI 2026
ProMed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLMs
ACL 2026
Can Knowledge Editing Really Correct Hallucinations?
ICLR 2025
Can Large Language Models Identify Authorship?
EMNLP 2024