How Do Decoder-Only LLMs Perceive Users? Rethinking Attention Masking for User Representation Learning
Paper
•
2602.10622
•
Published
•
26
Zhiyuan Wang
FoerKent
·
AI & ML interests
Conformal Prediction, Statistical Verification, Uncertainty Quantification, Uncertainty Decomposition.
Recent Activity
upvoted
a
paper
about 20 hours ago
How Do Decoder-Only LLMs Perceive Users? Rethinking Attention Masking for User Representation Learning
upvoted
a
paper
8 days ago
SafeGround: Know When to Trust GUI Grounding Models via Uncertainty Calibration
liked
a dataset
10 months ago
tau/commonsense_qa
Organizations
None yet