What Is Seen Cannot Be Unseen: The Disruptive Effect of Knowledge Conflict on Large Language Models
Paper
•
2506.06485
•
Published
•
5
Fan Bai
fbaigt
·
AI & ML interests
NLP & IE
Recent Activity
upvoted
a
paper
about 2 months ago
What Is Seen Cannot Be Unseen: The Disruptive Effect of Knowledge
Conflict on Large Language Models
upvoted
a
paper
10 months ago
Controllable Safety Alignment: Inference-Time Adaptation to Diverse
Safety Requirements
updated
a dataset
over 1 year ago
fbaigt/schema-to-json
Organizations
upvoted
a
paper
about 2 months ago