Are LLMs Vulnerable to Preference-Undermining Attacks (PUA)? A Factorial Analysis Methodology for Diagnosing the Trade-off between Preference Alignment and Real-World Validity
Paper
•
2601.06596
•
Published
•
11
Feng
hwindy
·
AI & ML interests
None yet
Recent Activity
Organizations
upvoted
a
paper
1 day ago