“Looks like grokking could give better reasoning and generalization to LLMs, but I'm not sure how practical it would be to overfit a larger LLM See: https://arxiv.org/abs/2405.15071”
Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization
We study whether transformers can learn to implicitly reason over parametric knowledge, a skill that even the most capable language models struggle with. Focusing on two representative reasoning types, composition and comparison, we consistently find that transformers can learn implicit reasoning, but only through grokking, i.e., extended training far beyond overfitting. The levels of generalization also vary across reasoning types: when faced with out-of-distribution examples, transformers fail to systematically generalize for composition but succeed for comparison. We delve into the model's internals throughout training, conducting analytical experiments that reveal: 1) the mechanism behind grokking, such as the formation of the generalizing circuit and its relation to the relative efficiency of generalizing and memorizing circuits, and 2) the connection between systematicity and the configuration of the generalizing circuit. Our findings guide data and training setup to better induce implicit reasoning and suggest potential improvements to the transformer architecture, such as encouraging cross-layer knowledge sharing. Furthermore, we demonstrate that for a challenging reasoning task with a large search space, GPT-4-Turbo and Gemini-1.5-Pro based on non-parametric memory fail badly regardless of prompting styles or retrieval augmentation, while a fully grokked transformer can achieve near-perfect accuracy, showcasing the power of parametric memory for complex reasoning.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及“According to https://arxiv.org/abs/2405.15071 their grokked model outperformed GPT4 and Gemini1.5 on the reasoning task. We can then argue if the task makes sense and the conclusion stands for other use cases but i think grokking can be useful”
“> grokking doesn't and will not have practical uses, imo I'm not so sure. Reasoning is the next big hurdle, and grokking and parametric memory seem very effective here. [1] https://arxiv.org/abs/2405.15071”
“> The practice of solving problems that you describe is to ingrain/memorize those steps so you don't forget how to apply the procedure correctly Simply memorizing sequences of steps is not how mathematics learning works, otherwise we would not see so much variation in outcomes. Me and Terence Tao on the same exact math training data would not yield two m…”
“While I agree with the sentiment in general, I've came to the conclusion that what I really want is the flexibility of the natural language interface that LLM's provide, and the return of the correct document. No 'reasoning', no summarizing, just better search [0]. The issue with the current generation of models is that they can't reason, they may do ver…”
- Grokked Transformers Are Implicit Reasoners ↗frednoodle · 2024-05-27 · 4 分
- Grokked Transformers Are Implicit Reasoners ↗jasondavies · 2024-05-27 · 239 分