News for hackers. Stuff that matters.
Re:LLMs cannot find reasoning errors, but can correct them by galaxyLogic on Monday November 20, 2023 @09:34PM (#38358245)
If your prompt-input is high quality it is more likely to match high-quality training inputs
Re:LLMs cannot find reasoning errors, but can correct them by euroderf on Tuesday November 21, 2023 @02:25AM (#38360470)
This seems intuitively true but has it been established ?
Re:LLMs cannot find reasoning errors, but can correct them by galaxyLogic on Tuesday November 21, 2023 @11:59AM (#38366355)
Not sure. But it does make sense like you say. The output must somehow correspond to the input, in a meaningful way, that is the purpose of LLMs. If you gave the LLM just one words as input who knows what the output would be. But if you give it more meaningful information it has more to work with, to give you an answer that more precisely matches your question.