<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>AI， on Abel</title>
    <link>https://chen-huaneng.github.io/tags/ai/</link>
    <description>Recent content in AI， on Abel</description>
    <generator>Hugo</generator>
    <language>zh</language>
    <lastBuildDate>Thu, 29 Oct 2026 10:44:53 +0800</lastBuildDate>
    <atom:link href="https://chen-huaneng.github.io/tags/ai/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>【AI】ChatGPT的使用技巧</title>
      <link>https://chen-huaneng.github.io/posts/2026/2026-10-29-chatgpt/</link>
      <pubDate>Thu, 29 Oct 2026 10:44:53 +0800</pubDate>
      <guid>https://chen-huaneng.github.io/posts/2026/2026-10-29-chatgpt/</guid>
      <description>介绍一些我在使用ChatGPT过程中会用到的小技巧。</description>
      <content:encoded><![CDATA[<h2 id="如何使用-chatgpt-搜索文献">如何使用 ChatGPT 搜索文献</h2>
<p>由于大语言模型自身以及训练数据集的缺陷（大语言模型的幻觉问题、学术文献数据集访问受限等），任何 AI 模型都有可能提供虚假的（不存在的）或者是错误的（不符合预期的）参考文献，因此如何正确使用 ChatGPT 去搜索想要的文献显得十分重要，根据我个人的使用经验，以下是一些可供参考的建议：</p>
<h3 id="提示词设计">提示词设计</h3>
<p>在提问前最重要的就是关于提示词的设计，提示词的设计根据想要搜索内容的不同而不同，但是有一些通用的提示词设计的要求（规则）可供参考：</p>
<h4 id="避免模糊的请求">避免模糊的请求</h4>
<p>如果用户使用宽泛或模糊的请求，ChatGPT 可能会编造虚假的参考文献。因此，应尽量使用具体、可验证的要求。</p>
<blockquote>
<p>错误示例：请提供 5 篇关于免疫疗法的参考文献。</p>
</blockquote>
<p>这样的问题会导致 ChatGPT 编造文献，而非提供真实可查的来源。</p>
<blockquote>
<p>优化示例：请仅提供可在 Google Scholar、Web of Science 或 PubMed 检索到的真实文献，并附 DOI 号。</p>
</blockquote>
<p>这个请求更精确，要求 ChatGPT 提供可验证的文献。</p>
<h4 id="使用具体的要求">使用具体的要求</h4>
<p>指定论文的时间范围、期刊、作者等，可以提高 ChatGPT 提供真实文献的概率。例如：</p>
<blockquote>
<p>请提供 2020 年后发表的关于癌症免疫治疗的论文，并给出 DOI 号。</p>
<p>请提供 Nature 或 Science 期刊上的真实论文，并附上完整引用格式。</p>
</blockquote>
<p>具体要求让 ChatGPT 更倾向于提供已知的真实论文，而非编造信息。</p>
<h4 id="让-chatgpt-仅提供已知文献">让 ChatGPT 仅提供已知文献</h4>
<p>ChatGPT 可能无法直接访问学术数据库，但它可以基于其训练数据提供一些已知的高被引论文，用户可以请求 ChatGPT 只列出已被广泛引用的文献。例如：</p>
<blockquote>
<p>请列出一些关于癌症免疫疗法的高被引论文，并附上 DOI 号和出处。</p>
<p>请列出 Google Scholar 上 2023 年后关于 CRISPR 技术的高被引论文，并提供 DOI。</p>
</blockquote>
<p>这些问题引导 ChatGPT 提供更具代表性的文献，而不是凭空编造的引用。</p>
<h3 id="实操案例">实操案例</h3>
<p>现在的目标是：</p>
<blockquote>
<p>如何使用ChatGPT查找并总结3年内（2026、2025、2024年）发表在Transportation Research Part B: Methodological、European Journal of Operational Research和Transportation Science期刊上的有关ALNS（Adaptive Large Neighborhood Search）算法在VRP（Vehicle Routing Problems）和TSP（Traveling Salesman Problem）及其相关变体等领域的文献</p>
</blockquote>
<p>提示词可以按照下面的模板进行设计，或者通过 AI 根据要求生成相应的提示词后进行修改：</p>
<div class="highlight"><pre tabindex="0" class="chroma"><code class="language-markdown" data-lang="markdown"><span class="line"><span class="ln">  1</span><span class="cl">你是一名运筹优化（Operations Research）与智能优化算法领域的研究人员，熟悉 Vehicle Routing Problem（VRP）、Traveling Salesman Problem（TSP）、Adaptive Large Neighborhood Search（ALNS）及其相关研究。
</span></span><span class="line"><span class="ln">  2</span><span class="cl">
</span></span><span class="line"><span class="ln">  3</span><span class="cl">我希望对2024—2026年发表在以下三本国际期刊中的 ALNS 相关研究进行尽可能全面、可复核的文献检索。
</span></span><span class="line"><span class="ln">  4</span><span class="cl">
</span></span><span class="line"><span class="ln">  5</span><span class="cl">【一、目标期刊】
</span></span><span class="line"><span class="ln">  6</span><span class="cl">
</span></span><span class="line"><span class="ln">  7</span><span class="cl"><span class="k">1.</span> Transportation Research Part B: Methodological
</span></span><span class="line"><span class="ln">  8</span><span class="cl"><span class="k">2.</span> European Journal of Operational Research
</span></span><span class="line"><span class="ln">  9</span><span class="cl"><span class="k">3.</span> Transportation Science
</span></span><span class="line"><span class="ln"> 10</span><span class="cl">
</span></span><span class="line"><span class="ln"> 11</span><span class="cl">【二、时间范围】
</span></span><span class="line"><span class="ln"> 12</span><span class="cl">
</span></span><span class="line"><span class="ln"> 13</span><span class="cl">2024年1月1日至2026年10月29日。
</span></span><span class="line"><span class="ln"> 14</span><span class="cl">
</span></span><span class="line"><span class="ln"> 15</span><span class="cl">同时检索正式发表和 Online First / Articles in Advance 论文。
</span></span><span class="line"><span class="ln"> 16</span><span class="cl">
</span></span><span class="line"><span class="ln"> 17</span><span class="cl">请分别记录首次在线发表年份和正式卷期年份，避免重复统计。
</span></span><span class="line"><span class="ln"> 18</span><span class="cl">
</span></span><span class="line"><span class="ln"> 19</span><span class="cl">【三、核心研究主题】
</span></span><span class="line"><span class="ln"> 20</span><span class="cl">
</span></span><span class="line"><span class="ln"> 21</span><span class="cl">重点检索以下问题：
</span></span><span class="line"><span class="ln"> 22</span><span class="cl">
</span></span><span class="line"><span class="ln"> 23</span><span class="cl"><span class="k">1.</span> Vehicle Routing Problem（VRP）
</span></span><span class="line"><span class="ln"> 24</span><span class="cl"><span class="k">2.</span> Traveling Salesman Problem（TSP）
</span></span><span class="line"><span class="ln"> 25</span><span class="cl"><span class="k">3.</span> Vehicle Routing Problem with Time Windows（VRPTW）
</span></span><span class="line"><span class="ln"> 26</span><span class="cl"><span class="k">4.</span> Pickup and Delivery Problem（PDP）
</span></span><span class="line"><span class="ln"> 27</span><span class="cl"><span class="k">5.</span> Electric Vehicle Routing Problem（EVRP）
</span></span><span class="line"><span class="ln"> 28</span><span class="cl"><span class="k">6.</span> Dynamic Vehicle Routing Problem（DVRP）
</span></span><span class="line"><span class="ln"> 29</span><span class="cl"><span class="k">7.</span> Multi-Depot Vehicle Routing Problem（MDVRP）
</span></span><span class="line"><span class="ln"> 30</span><span class="cl"><span class="k">8.</span> Traveling Salesman Problem with Time Windows（TSPTW）
</span></span><span class="line"><span class="ln"> 31</span><span class="cl"><span class="k">9.</span> Orienteering Problem（OP）
</span></span><span class="line"><span class="ln"> 32</span><span class="cl"><span class="k">10.</span> Prize-Collecting Traveling Salesman Problem（PCTSP）
</span></span><span class="line"><span class="ln"> 33</span><span class="cl"><span class="k">11.</span> Truck-Drone Routing Problem
</span></span><span class="line"><span class="ln"> 34</span><span class="cl"><span class="k">12.</span> Vehicle Routing Problem with Drone (VRP-D)
</span></span><span class="line"><span class="ln"> 35</span><span class="cl"><span class="k">13.</span> Two-Echelon Location Routing Problem (2E-LRP)
</span></span><span class="line"><span class="ln"> 36</span><span class="cl"><span class="k">14.</span> 其他具有路径规划、节点访问顺序优化、选址及路劲优化或车辆调度特征的组合优化问题。
</span></span><span class="line"><span class="ln"> 37</span><span class="cl">
</span></span><span class="line"><span class="ln"> 38</span><span class="cl">【四、算法检索范围】
</span></span><span class="line"><span class="ln"> 39</span><span class="cl">
</span></span><span class="line"><span class="ln"> 40</span><span class="cl">核心检索词：
</span></span><span class="line"><span class="ln"> 41</span><span class="cl">
</span></span><span class="line"><span class="ln"> 42</span><span class="cl"><span class="k">-</span> Adaptive Large Neighborhood Search
</span></span><span class="line"><span class="ln"> 43</span><span class="cl"><span class="k">-</span> ALNS
</span></span><span class="line"><span class="ln"> 44</span><span class="cl"><span class="k">-</span> Adaptive Large Neighbourhood Search
</span></span><span class="line"><span class="ln"> 45</span><span class="cl"><span class="k">-</span> Large Neighborhood Search
</span></span><span class="line"><span class="ln"> 46</span><span class="cl"><span class="k">-</span> Large Neighbourhood Search
</span></span><span class="line"><span class="ln"> 47</span><span class="cl"><span class="k">-</span> Hybrid ALNS
</span></span><span class="line"><span class="ln"> 48</span><span class="cl"><span class="k">-</span> Learning-based ALNS
</span></span><span class="line"><span class="ln"> 49</span><span class="cl"><span class="k">-</span> Reinforcement Learning ALNS
</span></span><span class="line"><span class="ln"> 50</span><span class="cl">
</span></span><span class="line"><span class="ln"> 51</span><span class="cl">其中，普通 LNS 论文需要单独标记，不得直接视为 ALNS 论文。
</span></span><span class="line"><span class="ln"> 52</span><span class="cl">
</span></span><span class="line"><span class="ln"> 53</span><span class="cl">【五、检索方法】
</span></span><span class="line"><span class="ln"> 54</span><span class="cl">
</span></span><span class="line"><span class="ln"> 55</span><span class="cl">请使用以下渠道交叉检索：
</span></span><span class="line"><span class="ln"> 56</span><span class="cl">
</span></span><span class="line"><span class="ln"> 57</span><span class="cl"><span class="k">1.</span> 三本期刊的官方网站
</span></span><span class="line"><span class="ln"> 58</span><span class="cl"><span class="k">2.</span> Google Scholar
</span></span><span class="line"><span class="ln"> 59</span><span class="cl"><span class="k">3.</span> Crossref
</span></span><span class="line"><span class="ln"> 60</span><span class="cl"><span class="k">4.</span> OpenAlex
</span></span><span class="line"><span class="ln"> 61</span><span class="cl"><span class="k">5.</span> Semantic Scholar
</span></span><span class="line"><span class="ln"> 62</span><span class="cl"><span class="k">6.</span> 其他可访问的可靠学术数据库
</span></span><span class="line"><span class="ln"> 63</span><span class="cl">
</span></span><span class="line"><span class="ln"> 64</span><span class="cl">请同时使用关键词检索、期刊限定检索、论文引用追踪和相关论文追踪。
</span></span><span class="line"><span class="ln"> 65</span><span class="cl">
</span></span><span class="line"><span class="ln"> 66</span><span class="cl">不仅检索标题和摘要，也尽可能检索论文正文中的算法名称。
</span></span><span class="line"><span class="ln"> 67</span><span class="cl">
</span></span><span class="line"><span class="ln"> 68</span><span class="cl">【六、文献筛选标准】
</span></span><span class="line"><span class="ln"> 69</span><span class="cl">
</span></span><span class="line"><span class="ln"> 70</span><span class="cl">优先纳入：
</span></span><span class="line"><span class="ln"> 71</span><span class="cl">
</span></span><span class="line"><span class="ln"> 72</span><span class="cl">A类：明确提出或改进 ALNS 算法的论文。
</span></span><span class="line"><span class="ln"> 73</span><span class="cl">
</span></span><span class="line"><span class="ln"> 74</span><span class="cl">B类：使用 ALNS 解决 VRP、TSP 或相关变体的论文。
</span></span><span class="line"><span class="ln"> 75</span><span class="cl">
</span></span><span class="line"><span class="ln"> 76</span><span class="cl">C类：将 ALNS 与其他算法结合的论文。
</span></span><span class="line"><span class="ln"> 77</span><span class="cl">
</span></span><span class="line"><span class="ln"> 78</span><span class="cl">D类：虽然没有直接使用 ALNS，但提出了具有重要借鉴价值的 LNS 或邻域搜索机制的论文。
</span></span><span class="line"><span class="ln"> 79</span><span class="cl">
</span></span><span class="line"><span class="ln"> 80</span><span class="cl">请将 A、B、C、D 四类分开。
</span></span><span class="line"><span class="ln"> 81</span><span class="cl">
</span></span><span class="line"><span class="ln"> 82</span><span class="cl">【七、输出要求】
</span></span><span class="line"><span class="ln"> 83</span><span class="cl">
</span></span><span class="line"><span class="ln"> 84</span><span class="cl">请首先输出一张完整的文献清单，以Excel文件的形式输出，包含：
</span></span><span class="line"><span class="ln"> 85</span><span class="cl">
</span></span><span class="line"><span class="ln"> 86</span><span class="cl"><span class="k">1.</span> 论文标题
</span></span><span class="line"><span class="ln"> 87</span><span class="cl"><span class="k">2.</span> 作者
</span></span><span class="line"><span class="ln"> 88</span><span class="cl"><span class="k">3.</span> 期刊名称
</span></span><span class="line"><span class="ln"> 89</span><span class="cl"><span class="k">4.</span> 首次在线发表年份
</span></span><span class="line"><span class="ln"> 90</span><span class="cl"><span class="k">5.</span> 正式卷期年份
</span></span><span class="line"><span class="ln"> 91</span><span class="cl"><span class="k">6.</span> DOI
</span></span><span class="line"><span class="ln"> 92</span><span class="cl"><span class="k">7.</span> 研究问题
</span></span><span class="line"><span class="ln"> 93</span><span class="cl"><span class="k">8.</span> 使用的算法
</span></span><span class="line"><span class="ln"> 94</span><span class="cl"><span class="k">9.</span> 是否使用 ALNS
</span></span><span class="line"><span class="ln"> 95</span><span class="cl"><span class="k">10.</span> 文献分类（A/B/C/D）
</span></span><span class="line"><span class="ln"> 96</span><span class="cl"><span class="k">11.</span> 是否可以获取全文
</span></span><span class="line"><span class="ln"> 97</span><span class="cl"><span class="k">12.</span> 信息核实状态
</span></span><span class="line"><span class="ln"> 98</span><span class="cl">
</span></span><span class="line"><span class="ln"> 99</span><span class="cl">按期刊、年份进行排序。
</span></span><span class="line"><span class="ln">100</span><span class="cl">
</span></span><span class="line"><span class="ln">101</span><span class="cl">【八、严格要求】
</span></span><span class="line"><span class="ln">102</span><span class="cl">
</span></span><span class="line"><span class="ln">103</span><span class="cl"><span class="k">1.</span> 不允许编造论文。
</span></span><span class="line"><span class="ln">104</span><span class="cl"><span class="k">2.</span> 每篇论文必须提供可核实的 DOI 或期刊官方页面。
</span></span><span class="line"><span class="ln">105</span><span class="cl"><span class="k">3.</span> 不得将其他期刊的论文混入目标期刊。
</span></span><span class="line"><span class="ln">106</span><span class="cl"><span class="k">4.</span> 不得把仅引用 ALNS 的论文当作使用 ALNS 的论文。
</span></span><span class="line"><span class="ln">107</span><span class="cl"><span class="k">5.</span> 不得将普通 LNS 自动归类为 ALNS。
</span></span><span class="line"><span class="ln">108</span><span class="cl"><span class="k">6.</span> 无法确认的信息标记为“待核实”。
</span></span><span class="line"><span class="ln">109</span><span class="cl"><span class="k">7.</span> 明确说明检索日期和检索覆盖范围。
</span></span><span class="line"><span class="ln">110</span><span class="cl"><span class="k">8.</span> 不得声称检索结果完全穷尽，除非有充分的数据库覆盖证据。
</span></span></code></pre></div>]]></content:encoded>
    </item>
  </channel>
</rss>
