Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers — mentioned by imtringued

Sat, 17 Aug 2024 13:29:35 GMT

Yeah, if an LLM was truly capable of reasoning, then whenever it makes a mistake, e.g. due to randomness or due to lack of knowledge, then pointing out the mistakes and giving steps on correcting the mistakes should result in basically a 100% success rate, since the assistant has infinite capacity to accommodate the LLM's weaknesses. When you look at things like https://arxiv.org/abs/2408.06195 you notice that the amount of tokens needed to solve trivial tasks is somewhat ridiculous. On the order of 300k tokens for a simple grade school problem. That is roughly three hours at a rate of 30…

Paper and discussion history. A mention is not an endorsement.

Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers — HN submission

Wed, 14 Aug 2024 16:33:16 GMT

Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers

4 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers · HackerPapers discussions

Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers — mentioned by imtringued

Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers — HN submission