From Decoding to Meta-Generation:Inference-time Algorithms for Large Language Models
One of the most striking findings in modern research on large language models (LLMs) is that scaling up compute during training leads to better results. However, less attention has been given to the benefits of scaling compute during inference. This survey focuses on these inference-time approaches. We explore three areas under a unified mathematical formalism:token-level generation algorithms, meta-generation algorithms, and efficient generation. Token-level generation algorithms, often called decoding algorithms, operate by sampling a single token at a time or constructing a token-level search space and then selecting an output. These methods typically assume access to a language model’s logits, next-token distributions, or probability scores. Meta-generation algorithms work on partial or full sequences, incorporating domain knowledge, enabling backtracking, and integrating external information. Efficient generation methods aim to reduce token costs and improve the speed of generation. Our survey unifies perspectives from three research communities:traditional natural language processing, modern LLMs, and machine learning systems.
多次取 (0, 1) 之间的随机实数, 期望多少次后其和恰不小于 1
用到了算期望中常用的容斥技巧和一种利用递推式巧算多重积分的技巧.
「ABC356F」Distance Component Size Query
「ABC356F」Distance Component Size Query 解题报告
某 0/1 背包 Trick
有 $n$ 个物品, 第 $i$ 个重量为 $a_i$, 求重量不大于 $c$ 的情况下能够装下的最大重量.
$n, m = \max\{a_i\} \leqslant 2 \times 10 ^ 4, c \leqslant 10 ^ 9.$