Extremely Sparse Supervision Incentivizes Reasoning Ability
Large language models demonstrate increasingly strong reasoning capabilities through effective post-training. Yet, prevailing post-training methods optimize over massive numbers of tokens, implicitly assuming that effective learning must be token-intensive. We revisit this assumption in the on-policy distillation (OPD)...
Zhi-Shuai Liu, Xingzi Xu, Mehmet Saygin Seyfioglu et al.
· 2 citations