vix.ing
·
top
·
new
·
best
·
stats
·
spec
Gabrielle Kaili-May Liu
Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs
2026/06/30 by
Gabrielle Kaili-May Liu
,
Avi Caciularu
,
Gal Yona
+2 · 4 voices
#cs.CL
#cs.AI