vix.ing
·
top
·
new
·
best
·
stats
·
spec
Song, Ruike
Causal Reward Adjustment: Mitigating Reward Hacking in External Reasoning via Backdoor Correction
2025/08/06 by
Song, Ruike
,
Song, Zeen
,
Guo, Huijie
+1 · 1 citation
#FOS: Computer and information sciences
#Machine Learning (cs.LG)