[hackinthebochs]

When it comes to logical reasoning, the difficulty isn't about having enough new information, but about ensuring the LLMs capture the right information. The problem LLMs have with learning logical reasoning from standard training is that they learn spurious relationships between the context and the next token, undermining its ability to learn fully general logical reasoning. Synthetic data helps because spurious associations are undermined by the randomness inherent in the synthetic data, forcing the model to find the right generic reasoning steps.

[jeremyjh]

I agree! DeepSeek has shown this is incredibly powerful. I think their Qwen 8B model may be as good as GPT4’s flagship. And I can run it on my laptop if it’s not on my lap. But the amount of synthetic data you can generate is bounded by the raw information, so I don’t think it’s an answer to the SP.