Sharpening Tax in Post-Training
An emerging hypothesis about reinforcement learning (RL) post-training of large language models (LLMs) is that it merely sharpens existing behaviors of a base model, improving single-shot accuracy at the cost of solution coverage. Although this trade-off has been observed in math and coding tasks, it need not extend to...
Changdae Oh, Qi Zeng, Qi Qi et al.
· 0 citations