Фото: David Mdzinarishvili / Reuters
Even though my dataset is very small, I think it's sufficient to conclude that LLMs can't consistently reason. Also their reasoning performance gets worse as the SAT instance grows, which may be due to the context window becoming too large as the model reasoning progresses, and it gets harder to remember original clauses at the top of the context. A friend of mine made an observation that how complex SAT instances are similar to working with many rules in large codebases. As we add more rules, it gets more and more likely for LLMs to forget some of them, which can be insidious. Of course that doesn't mean LLMs are useless. They can be definitely useful without being able to reason, but due to lack of reasoning, we can't just write down the rules and expect that LLMs will always follow them. For critical requirements there needs to be some other process in place to ensure that these are met.
。关于这个话题，旺商聊官方下载提供了深入分析
第九十九条 人民警察询问被侵害人或者其他证人，可以在现场进行，也可以到其所在单位、住处或者其提出的地点进行；必要时，也可以通知其到公安机关提供证言。
But there are plenty of wild cards ahead, as Ullrich and others are quick to acknowledge.
我的「發音測試」結果（也就是需要我大聲說出聲調的部分）就沒那麼亮眼了，從 38% 提升到第三天的 55%，雖然如此，雷布夏特安慰我說，這樣的分數已遠高於隨機猜測的機率。