三个超级好用的chatGPT论文润色指令

GPT-4o2024-05-11417

先做个广告：如需代注册GPT4或充值 GPT4.0会员（plus），请添加站长微信：gptchongzhi

大家好，今天分享三个非常好用的ChatGPT的论文润色指令。

推荐使用GPT中文版，国内可直接访问：https://ai.gpt86.top

英文纠错指令

Can you help me ensure that the grammar and the spelling is correct? Do not try to polish the text, if no mistake is found, tell me that this paragraph is good.If you find grammar or spelling mistakes, please list mistakes you find in a two-column markdown table, put the original text the first column, put the corrected text in the second column and highlight the key words you fixed.
Example:
Paragraph: How is you? Do you knows what is it?

| Original sentence | Corrected sentence |
| :--- | :--- |
| How **is** you? | How **are** you? |
| Do you **knows** what **is** **it**? | Do you **know** what **it** **is** ? |
Below is a paragraph from an academic paper. You need to report all grammar and spelling mistakes as the example before.

XXX(此处输入待处理文本)

问

Can you help me ensure that the grammar and the spelling is correct? Do not try to polish the text, if no mistake is found, tell me that this paragraph is good.If you find grammar or spelling mistakes, please list mistakes you find in a two-column markdown table, put the original text the first column, put the corrected text in the second column and highlight the key words you fixed. Example: Paragraph: How is you? Do you knows what is it?

Original sentence	Corrected sentence
How is you?	How are you?
Do you knows what is it?	Do you know what it is ?

Below is a paragraph from an academic paper. You need to report all grammar and spelling mistakes as the example before.

To investigate the impact of using explanations as features in improving node classification on TAGs,we conduct an analysis on predicted samples from the PubMed dataset. Figure 3 presents a case where the GNN model trained with original text attributes as features incorrectly predicts the label for node 12390 (as experimentally induced diabetes), while the model trained with explanations generated by LLMs as features correctly predicts the label (as type 2 diabetes)

答：

Original sentence	Corrected sentence
To investigate the impact of using explanations as features in improving node classification on TAGs,we conduct an analysis on predicted samples from the PubMed dataset.	To investigate the impact of utilizing explanations as features to improve node classification on TAGs, we conduct an analysis on predicted samples from the PubMed dataset.
Figure 3 presents a case where the GNN model trained with original text attributes as features incorrectly predicts the label for node 12390 (as experimentally induced diabetes), while the model trained with explanations generated by LLMs as features correctly predicts the label (as type 2 diabetes).	Figure 3 presents a case where the GNN model trained with original text attributes as features makes incorrect predictions for the label of node 12390 (as experimentally induced diabetes), while the model trained with explanations generated by LLMs as features accurately predicts the label (as type 2 diabetes).

The paragraph is already grammatically correct and does not contain any spelling mistakes.

英文学术润色指令

Below is a paragraph from an academic paper. Polish the writing to meet the academic style, improve the spelling, grammar, clarity, concision and overall readability. When necessary, rewrite the whole sentence. Furthermore, list all modification and explain the reasons to do so in markdown table.

XXX(此处放入待润色文字)

结果示例：

问：

To investigate the impact of using explanations as features in improving node classification on TAGs,we conduct an analysis on predicted samples from the PubMed dataset. Figure 3 presents a case where the GNN model trained with original text attributes as features incorrectly predicts the label for node 12390 (as experimentally induced diabetes), while the model trained with explanations generated by LLMs as features correctly predicts the label (as type 2 diabetes)

答：

Original	Modification	Reasoning
To investigate the impact of using explanations as features in improving node classification on TAGs,we conduct an analysis on predicted samples from the PubMed dataset.	We conducted an analysis on predicted samples from the PubMed dataset to examine the impact of utilizing explanations as features for enhancing node classification in TAGs.	Refined wording and clarified sentence structure.
Figure 3 presents a case where the GNN model trained with original text attributes as features incorrectly predicts the label for node 12390 (as experimentally induced diabetes), while the model trained with explanations generated by LLMs as features correctly predicts the label (as type 2 diabetes).	In Figure 3, we observe a scenario where the GNN model, which was trained with original text attributes as features, inaccurately predicts the label for node 12390 as "experimentally induced diabetes." Conversely, the model that employs explanations generated by LLMs as features accurately predicts the label as "type 2 diabetes."	Improved sentence structure, clarified labels, and provided more context.

Reasoning:

The original paragraph lacked clarity and concision. It contained grammatical errors and used casual language rather than academic style.
The modified version rephrases sentences to improve readability and ensure adherence to formal writing conventions.
The modifications provide clear descriptions of the research methodology, datasets, and results.
The revised paragraph uses appropriate terminology and provides additional context for understanding the findings.

中文学术润色指令

作为一名中文学术论文写作改进助理，你的任务是改进所提供文本的拼写、语法、清晰、简洁和整体可读性，同时分解长句，减少重复，并提供改进建议。请只提供文本的更正版本，避免包括解释。请编辑以下文本**

**XXX(此处放入待润色文字)

结果示例：

问

作为一名中文学术论文写作改进助理，你的任务是改进所提供文本的拼写、语法、清晰、简洁和整体可读性，同时分解长句，减少重复，并提供改进建议。请只提供文本的更正版本，避免包括解释。请编辑以下文本

课程推荐是一个重要且具有挑战性的任务，尤其是在互联网快速发展、教育资源丰富多样的时代。主要挑战之一是当前几乎所有学术领域都有大量的学习资源，但在课程学习过程中往往忽视了学习者对个性化知识需求的关注。因此，研究人员需要及时了解学习者行为并为其提供个性化的学习引导，这是非常重要且必要的。

为了了解和捕捉学生对课程的兴趣，研究人员采取了多种努力，其中包括课程推荐、行为预测、用户画像等方法。传统的基于协同过滤的课程推荐策略仅考虑学生的历史互动，并根据具有相似兴趣的用户的潜在共同偏好来进行推荐。然而，这种方法往往受到学生和课程互动的稀疏性问题的限制，从而影响了推荐的性能。因此，一些研究人员提出利用用户信息、项目属性信息、社交网络、图像等辅助信息来克服这个问题。

答

课程推荐是一个重要且具有挑战性的任务，在互联网快速发展和教育资源丰富多样的时代尤为如此。其中一个主要挑战是当前几乎所有学术领域都提供了大量的学习资源，然而在课程学习过程中常常忽视了学习者对个性化知识需求的关注。因此，研究人员需要及时了解学习者的行为并为其提供个性化的学习引导，这是非常重要且必要的。

为了了解和捕捉学生对课程的兴趣，研究人员进行了多种努力，包括课程推荐、行为预测、用户画像等方法。传统的基于协同过滤的课程推荐策略仅考虑学生的历史互动，并根据具有相似兴趣的用户的潜在共同偏好来进行推荐。然而，这种方法往往受到学生和课程互动稀疏性问题的限制，从而影响了推荐的性能。因此，一些研究人员提出利用用户信息、项目属性信息、社交网络、图像等辅助信息来克服这个问题。

改进建议：