Causal Reward Adjustment: Mitigating Reward Hacking in External Reasoning via Backdoor Correction.
Ruike Song, Zeen Song, Huijie Guo, Wenwen Qiang
Browse the full AAAI paper archive.
Ruike Song, Zeen Song, Huijie Guo, Wenwen Qiang
Browse the full AAAI paper archive.