市值: $2.1403T -1.80%
成交额(24h): $76.2115B -13.96%
  • 市值: $2.1403T -1.80%
  • 成交额(24h): $76.2115B -13.96%
  • 恐惧与贪婪指数:
  • 市值: $2.1403T -1.80%
加密货币
话题
百科
资讯
加密话题
视频
热门新闻
加密货币
话题
百科
资讯
加密话题
视频
bitcoin
bitcoin

$87959.907984 USD

1.34%

ethereum
ethereum

$2920.497338 USD

3.04%

tether
tether

$0.999775 USD

0.00%

xrp
xrp

$2.237324 USD

8.12%

bnb
bnb

$860.243768 USD

0.90%

solana
solana

$138.089498 USD

5.43%

usd-coin
usd-coin

$0.999807 USD

0.01%

tron
tron

$0.272801 USD

-1.53%

dogecoin
dogecoin

$0.150904 USD

2.96%

cardano
cardano

$0.421635 USD

1.97%

hyperliquid
hyperliquid

$32.152445 USD

2.23%

bitcoin-cash
bitcoin-cash

$533.301069 USD

-1.94%

chainlink
chainlink

$12.953417 USD

2.68%

unus-sed-leo
unus-sed-leo

$9.535951 USD

0.73%

zcash
zcash

$521.483386 USD

-2.87%

加密货币新闻

高级即时工程:思想链 (CoT)

2024/12/23 22:06

比较不同的推理技术

高级即时工程:思想链 (CoT)

Chain of Thought (CoT) techniques have been around for a while now, and they're essentially a form of advanced prompt engineering. CoT aims to get large language models (LLMs) to perform reasoning steps by explicitly showing them the chain of thought that leads to the answer. This helps the models understand the problem better and makes their reasoning more transparent.

思想链 (CoT) 技术已经存在一段时间了,它们本质上是高级提示工程的一种形式。 CoT 的目标是通过明确地向大型语言模型 (LLM) 展示导致答案的思维链来让大型语言模型 (LLM) 执行推理步骤。这有助于模型更好地理解问题并使他们的推理更加透明。

There are several different CoT techniques, each with its own strengths and weaknesses. Some of the most common techniques include:

有多种不同的 CoT 技术,每种技术都有自己的优点和缺点。一些最常见的技术包括:

* **Natural language CoT:** This technique uses natural language to describe the chain of thought. For example, to solve a math problem, you might write out the steps of the calculation in English.

* **自然语言CoT:** 该技术使用自然语言来描述思想链。例如,要解决数学问题,您可以用英语写出计算步骤。

* **Logical form CoT:** This technique uses a formal logical language to represent the chain of thought. This makes the reasoning more precise and easier to follow, but it can also be more difficult to create.

* **逻辑形式CoT:** 该技术使用形式逻辑语言来表示思想链。这使得推理更加精确且更容易遵循,但也可能更难以创建。

* **Programmatic CoT:** This technique uses a programming language to represent the chain of thought. This is the most precise and efficient way to represent reasoning, but it also requires the most technical knowledge to create.

* **Programmatic CoT:** 这种技术使用编程语言来表示思想链。这是最精确、最有效的表示推理的方式,但它也需要最多的技术知识来创建。

The best CoT technique to use will depend on the specific task and the capabilities of the LLM. However, all CoT techniques can help LLMs to perform reasoning tasks more effectively and transparently.

使用的最佳 CoT 技术将取决于具体任务和法学硕士的能力。然而,所有 CoT 技术都可以帮助法学硕士更有效、更透明地执行推理任务。

Here's an example of how CoT can be used to solve a math problem:

以下是如何使用 CoT 解决数学问题的示例:

Without CoT, the LLM might simply be given the problem and asked to solve it. For example:

如果没有 CoT,法学硕士可能会简单地提出问题并要求解决它。例如:

```

````

Question: What is 123 + 456?

问题:123+456是多少?

Answer: 579

答案:579

```

````

With CoT, the LLM would be given a step-by-step guide on how to solve the problem. For example:

通过 CoT,法学硕士将获得如何解决问题的分步指南。例如:

```

````

Question: What is 123 + 456?

问题:123+456是多少?

Chain of Thought:

思路链:

1. Add the tens digits (2 + 5 = 7).

1. 将十位数字相加 (2 + 5 = 7)。

2. Add the hundreds digits (1 + 4 = 5).

2. 将百位数字相加 (1 + 4 = 5)。

3. Add the results of steps 1 and 2 (7 + 5 = 12).

3. 将步骤 1 和 2 的结果相加 (7 + 5 = 12)。

4. Write down the carry digit (2).

4. 记下进位数字 (2)。

5. Add the ones digits (3 + 6 = 9).

5. 将个位数字相加 (3 + 6 = 9)。

6. Write down the sum of steps 4 and 5 (2 + 9 = 11).

6. 写下步骤 4 和 5 的总和 (2 + 9 = 11)。

7. The final answer is the result of step 6 (11).

7. 最终答案是步骤6(11)的结果。

Answer: 579

答案:579

```

````

By showing the LLM the chain of thought, we can help it to understand the problem better and arrive at the correct answer more easily.

通过向LLM展示思路链,我们可以帮助其更好地理解问题,更容易得出正确的答案。

CoT techniques are a powerful tool for improving the performance of LLMs on reasoning tasks. By making the reasoning process more explicit and transparent, CoT helps the models to learn and generalize better.

CoT 技术是提高法学硕士推理任务表现的强大工具。通过使推理过程更加明确和透明,CoT 帮助模型更好地学习和泛化。

原文来源:towardsdatascience

免责声明:info@kdj.com

所提供的信息并非交易建议。根据本文提供的信息进行的任何投资,kdj.com不承担任何责任。加密货币具有高波动性,强烈建议您深入研究后,谨慎投资!

如您认为本网站上使用的内容侵犯了您的版权,请立即联系我们(info@kdj.com),我们将及时删除。

2026年07月09日 发表的其他文章