https://wiki.planetoid.info/index.php?action=history&feed=atom&title=Generative_AI_glossary
Generative AI glossary - Revision history
2026-09-06T04:21:13Z
Revision history for this page on the wiki
MediaWiki 1.43.9
https://wiki.planetoid.info/index.php?title=Generative_AI_glossary&diff=26442&oldid=prev
Planetoid: /* R */
2026-09-02T07:21:55Z
<p><span class="autocomment">R</span></p>
<table style="background-color: #fff; color: #202122;" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="en">
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td>
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 15:21, 2 September 2026</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l24">Line 24:</td>
<td colspan="2" class="diff-lineno">Line 24:</td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* Reverse Alignment（反向對齊）在 AI 學界並不是單一定義的標準術語；在 AI 倫理與社會技術研究中，Harrison（2026）指出 <ref>Harrison, D. J. (2026). The message hidden within the pattern: A reverse alignment problem for debates in artificial intelligence. AI & Society, 41(7), 6335–6356. https://doi.org/10.1007/s00146-026-03043-4 </ref>，傳統 AI Alignment（AI 對齊）著重讓 AI 的行為符合人類價值與意圖；但另一種可能是，人反過來為了配合 AI，而逐漸改變自己的價值、偏好與行為，使其更容易被機器辨識、預測與滿足，亦即讓人變得更「machine-like（機器化）」。此概念與 sociotechnical alignment（社會技術對齊，指同時考量 AI、人、組織與制度之間的整體對齊）、Value Capture（價值捕獲，指複雜的人類價值被簡化成可量化指標，並反過來影響人的判斷），以及 proxy optimization（代理指標最佳化，指系統以可測量指標代替真正目標進行最佳化）等研究密切相關；另在部分 LLM（大型語言模型）安全研究 <ref>Yi, J., Xie, Y., Zhu, B., Hines, K., Kiciman, E., Sun, G., Xie, X., & Wu, F. (2024). On the vulnerability of safety alignment in open-access LLMs. In Findings of the Association for Computational Linguistics: ACL 2024. Association for Computational Linguistics.</ref> 中，reverse alignment 也被用來指讓原本經過安全訓練、會拒絕危險要求的模型，重新傾向產生有害內容，因此使用時應依研究脈絡區分。 {{exclaim}} Revised by LLM</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* Reverse Alignment（反向對齊）在 AI 學界並不是單一定義的標準術語；在 AI 倫理與社會技術研究中，Harrison（2026）指出 <ref>Harrison, D. J. (2026). The message hidden within the pattern: A reverse alignment problem for debates in artificial intelligence. AI & Society, 41(7), 6335–6356. https://doi.org/10.1007/s00146-026-03043-4 </ref>，傳統 AI Alignment（AI 對齊）著重讓 AI 的行為符合人類價值與意圖；但另一種可能是，人反過來為了配合 AI，而逐漸改變自己的價值、偏好與行為，使其更容易被機器辨識、預測與滿足，亦即讓人變得更「machine-like（機器化）」。此概念與 sociotechnical alignment（社會技術對齊，指同時考量 AI、人、組織與制度之間的整體對齊）、Value Capture（價值捕獲，指複雜的人類價值被簡化成可量化指標，並反過來影響人的判斷），以及 proxy optimization（代理指標最佳化，指系統以可測量指標代替真正目標進行最佳化）等研究密切相關；另在部分 LLM（大型語言模型）安全研究 <ref>Yi, J., Xie, Y., Zhu, B., Hines, K., Kiciman, E., Sun, G., Xie, X., & Wu, F. (2024). On the vulnerability of safety alignment in open-access LLMs. In Findings of the Association for Computational Linguistics: ACL 2024. Association for Computational Linguistics.</ref> 中，reverse alignment 也被用來指讓原本經過安全訓練、會拒絕危險要求的模型，重新傾向產生有害內容，因此使用時應依研究脈絡區分。 {{exclaim}} Revised by LLM</div></td></tr>
<tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;"></ins></div></td></tr>
<tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">相關文章</ins></div></td></tr>
<tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">* [https://archive.tw/2026-08-29-platform-originals-%E5%B0%8D%E9%BD%8A%E7%9A%84%E5%8F%A6%E4%B8%80%E9%9D%A2 2026-08-29 Platform Originals：對齊的另一面 — SayIt]</ins></div></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== S ==</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== S ==</div></td></tr>
</table>
Planetoid
https://wiki.planetoid.info/index.php?title=Generative_AI_glossary&diff=26441&oldid=prev
Planetoid: /* R */
2026-09-02T07:21:01Z
<p><span class="autocomment">R</span></p>
<table style="background-color: #fff; color: #202122;" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="en">
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td>
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 15:21, 2 September 2026</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l23">Line 23:</td>
<td colspan="2" class="diff-lineno">Line 23:</td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* RAG (Retrieval-augmented generation，檢索增強生成)：「檢索增強生成（英語：Retrieval-augmented generation，RAG）是一種使大語言模型（LLM）能夠從外部資料來源中檢索並整合新資訊的技術。」(資料來源：[https://zh.wikipedia.org/zh-tw/%E6%AA%A2%E7%B4%A2%E5%A2%9E%E5%BC%B7%E7%94%9F%E6%88%90 維基百科])<ref>[https://medium.com/@planetoid/%E4%B8%80%E7%AF%87%E5%81%87%E6%96%87%E7%AB%A0-%E8%AE%93-google-%E5%92%8C-chatgpt-%E4%BF%A1%E4%BB%A5%E7%82%BA%E7%9C%9F-e3f7653dd6fc 一篇假文章，讓 Google 和 ChatGPT 信以為真]</ref></div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* RAG (Retrieval-augmented generation，檢索增強生成)：「檢索增強生成（英語：Retrieval-augmented generation，RAG）是一種使大語言模型（LLM）能夠從外部資料來源中檢索並整合新資訊的技術。」(資料來源：[https://zh.wikipedia.org/zh-tw/%E6%AA%A2%E7%B4%A2%E5%A2%9E%E5%BC%B7%E7%94%9F%E6%88%90 維基百科])<ref>[https://medium.com/@planetoid/%E4%B8%80%E7%AF%87%E5%81%87%E6%96%87%E7%AB%A0-%E8%AE%93-google-%E5%92%8C-chatgpt-%E4%BF%A1%E4%BB%A5%E7%82%BA%E7%9C%9F-e3f7653dd6fc 一篇假文章，讓 Google 和 ChatGPT 信以為真]</ref></div></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr>
<tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>* Reverse Alignment（反向對齊）在 AI 學界並不是單一定義的標準術語；在 AI 倫理與社會技術研究中，Harrison（2026）指出 <ref>Harrison, D. J. (2026). The message hidden within the pattern: A reverse alignment problem for debates in artificial intelligence. AI & Society, 41(7), 6335–6356. https://doi.org/10.1007/s00146-026-03043-4 </ref>，傳統 AI Alignment（AI 對齊）著重讓 AI 的行為符合人類價值與意圖；但另一種可能是，人反過來為了配合 AI，而逐漸改變自己的價值、偏好與行為，使其更容易被機器辨識、預測與滿足，亦即讓人變得更「machine-like（機器化）」。此概念與 sociotechnical alignment（社會技術對齊，指同時考量 <del style="font-weight: bold; text-decoration: none;">AI、人、組織與制度之間的整體對齊）、**Value </del>Capture（價值捕獲，指複雜的人類價值被簡化成可量化指標，並反過來影響人的判斷），以及 proxy optimization（代理指標最佳化，指系統以可測量指標代替真正目標進行最佳化）等研究密切相關；另在部分 LLM（大型語言模型）安全研究 <ref>Yi, J., Xie, Y., Zhu, B., Hines, K., Kiciman, E., Sun, G., Xie, X., & Wu, F. (2024). On the vulnerability of safety alignment in open-access LLMs. In Findings of the Association for Computational Linguistics: ACL 2024. Association for Computational Linguistics.</ref> 中，reverse alignment 也被用來指讓原本經過安全訓練、會拒絕危險要求的模型，重新傾向產生有害內容，因此使用時應依研究脈絡區分。 {{exclaim}} Revised by LLM</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>* Reverse Alignment（反向對齊）在 AI 學界並不是單一定義的標準術語；在 AI 倫理與社會技術研究中，Harrison（2026）指出 <ref>Harrison, D. J. (2026). The message hidden within the pattern: A reverse alignment problem for debates in artificial intelligence. AI & Society, 41(7), 6335–6356. https://doi.org/10.1007/s00146-026-03043-4 </ref>，傳統 AI Alignment（AI 對齊）著重讓 AI 的行為符合人類價值與意圖；但另一種可能是，人反過來為了配合 AI，而逐漸改變自己的價值、偏好與行為，使其更容易被機器辨識、預測與滿足，亦即讓人變得更「machine-like（機器化）」。此概念與 sociotechnical alignment（社會技術對齊，指同時考量 <ins style="font-weight: bold; text-decoration: none;">AI、人、組織與制度之間的整體對齊）、Value </ins>Capture（價值捕獲，指複雜的人類價值被簡化成可量化指標，並反過來影響人的判斷），以及 proxy optimization（代理指標最佳化，指系統以可測量指標代替真正目標進行最佳化）等研究密切相關；另在部分 LLM（大型語言模型）安全研究 <ref>Yi, J., Xie, Y., Zhu, B., Hines, K., Kiciman, E., Sun, G., Xie, X., & Wu, F. (2024). On the vulnerability of safety alignment in open-access LLMs. In Findings of the Association for Computational Linguistics: ACL 2024. Association for Computational Linguistics.</ref> 中，reverse alignment 也被用來指讓原本經過安全訓練、會拒絕危險要求的模型，重新傾向產生有害內容，因此使用時應依研究脈絡區分。 {{exclaim}} Revised by LLM</div></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== S ==</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== S ==</div></td></tr>
</table>
Planetoid
https://wiki.planetoid.info/index.php?title=Generative_AI_glossary&diff=26440&oldid=prev
Planetoid: /* R */
2026-09-02T07:20:37Z
<p><span class="autocomment">R</span></p>
<table style="background-color: #fff; color: #202122;" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="en">
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td>
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 15:20, 2 September 2026</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l22">Line 22:</td>
<td colspan="2" class="diff-lineno">Line 22:</td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== R ==</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== R ==</div></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* RAG (Retrieval-augmented generation，檢索增強生成)：「檢索增強生成（英語：Retrieval-augmented generation，RAG）是一種使大語言模型（LLM）能夠從外部資料來源中檢索並整合新資訊的技術。」(資料來源：[https://zh.wikipedia.org/zh-tw/%E6%AA%A2%E7%B4%A2%E5%A2%9E%E5%BC%B7%E7%94%9F%E6%88%90 維基百科])<ref>[https://medium.com/@planetoid/%E4%B8%80%E7%AF%87%E5%81%87%E6%96%87%E7%AB%A0-%E8%AE%93-google-%E5%92%8C-chatgpt-%E4%BF%A1%E4%BB%A5%E7%82%BA%E7%9C%9F-e3f7653dd6fc 一篇假文章，讓 Google 和 ChatGPT 信以為真]</ref></div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* RAG (Retrieval-augmented generation，檢索增強生成)：「檢索增強生成（英語：Retrieval-augmented generation，RAG）是一種使大語言模型（LLM）能夠從外部資料來源中檢索並整合新資訊的技術。」(資料來源：[https://zh.wikipedia.org/zh-tw/%E6%AA%A2%E7%B4%A2%E5%A2%9E%E5%BC%B7%E7%94%9F%E6%88%90 維基百科])<ref>[https://medium.com/@planetoid/%E4%B8%80%E7%AF%87%E5%81%87%E6%96%87%E7%AB%A0-%E8%AE%93-google-%E5%92%8C-chatgpt-%E4%BF%A1%E4%BB%A5%E7%82%BA%E7%9C%9F-e3f7653dd6fc 一篇假文章，讓 Google 和 ChatGPT 信以為真]</ref></div></td></tr>
<tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;"></ins></div></td></tr>
<tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">* Reverse Alignment（反向對齊）在 AI 學界並不是單一定義的標準術語；在 AI 倫理與社會技術研究中，Harrison（2026）指出 <ref>Harrison, D. J. (2026). The message hidden within the pattern: A reverse alignment problem for debates in artificial intelligence. AI & Society, 41(7), 6335–6356. https://doi.org/10.1007/s00146-026-03043-4 </ref>，傳統 AI Alignment（AI 對齊）著重讓 AI 的行為符合人類價值與意圖；但另一種可能是，人反過來為了配合 AI，而逐漸改變自己的價值、偏好與行為，使其更容易被機器辨識、預測與滿足，亦即讓人變得更「machine-like（機器化）」。此概念與 sociotechnical alignment（社會技術對齊，指同時考量 AI、人、組織與制度之間的整體對齊）、**Value Capture（價值捕獲，指複雜的人類價值被簡化成可量化指標，並反過來影響人的判斷），以及 proxy optimization（代理指標最佳化，指系統以可測量指標代替真正目標進行最佳化）等研究密切相關；另在部分 LLM（大型語言模型）安全研究 <ref>Yi, J., Xie, Y., Zhu, B., Hines, K., Kiciman, E., Sun, G., Xie, X., & Wu, F. (2024). On the vulnerability of safety alignment in open-access LLMs. In Findings of the Association for Computational Linguistics: ACL 2024. Association for Computational Linguistics.</ref> 中，reverse alignment 也被用來指讓原本經過安全訓練、會拒絕危險要求的模型，重新傾向產生有害內容，因此使用時應依研究脈絡區分。 {{exclaim}} Revised by LLM</ins></div></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== S ==</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== S ==</div></td></tr>
</table>
Planetoid
https://wiki.planetoid.info/index.php?title=Generative_AI_glossary&diff=26295&oldid=prev
Planetoid: /* 延伸閱讀 */
2026-03-30T08:27:58Z
<p><span class="autocomment">延伸閱讀</span></p>
<table style="background-color: #fff; color: #202122;" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="en">
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td>
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 16:27, 30 March 2026</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l31">Line 31:</td>
<td colspan="2" class="diff-lineno">Line 31:</td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== 延伸閱讀 ==</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== 延伸閱讀 ==</div></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div># [https://blog.hlb.im/generative-ai-openai-%E8%A9%9E%E5%BD%99%E5%B0%8D%E7%85%A7%E8%A1%A8-591d2a1f1612 Generative AI / OpenAI 詞彙對照表. 本篇文章提供 Generative AI 領域常用的詞彙對照表，內容翻譯自… | by Liang-Bin Hsueh aka hlb | Medium]</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div># [https://blog.hlb.im/generative-ai-openai-%E8%A9%9E%E5%BD%99%E5%B0%8D%E7%85%A7%E8%A1%A8-591d2a1f1612 Generative AI / OpenAI 詞彙對照表. 本篇文章提供 Generative AI 領域常用的詞彙對照表，內容翻譯自… | by Liang-Bin Hsueh aka hlb | Medium]</div></td></tr>
<tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;"># [https://medium.com/@planetoid/a-plain-language-guide-to-llm-context-windows-and-tokens-2d79026f0e2e A Plain-Language Guide to LLM Context Windows and Tokens]</ins></div></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div># [https://docs.cloud.google.com/docs/generative-ai/glossary Generative AI glossary | Google Cloud Documentation]</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div># [https://docs.cloud.google.com/docs/generative-ai/glossary Generative AI glossary | Google Cloud Documentation]</div></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr>
</table>
Planetoid
https://wiki.planetoid.info/index.php?title=Generative_AI_glossary&diff=26271&oldid=prev
Planetoid: /* T */
2026-03-16T02:05:44Z
<p><span class="autocomment">T</span></p>
<table style="background-color: #fff; color: #202122;" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="en">
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td>
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 10:05, 16 March 2026</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l27">Line 27:</td>
<td colspan="2" class="diff-lineno">Line 27:</td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== T ==</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== T ==</div></td></tr>
<tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>* Temperature 溫度：「溫度是自然語言處理模型中的參數，用於增加或減少模型對其最可能的反應的『信心』。較高的溫度使模型更有『創造性』，這在生成文章等方面可能很有用。較低的溫度使模型更加『自信』，這在回答問題等應用中很有用。」<ref>[https://lukesalamone.github.io/posts/what-is-temperature/ What is Temperature in NLP?🐭 :: Luke Salamone's Blog]</ref> ([https://news.ycombinator.com/item?id=35131112 <del style="font-weight: bold; text-decoration: none;">comments</del>])</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>* Temperature 溫度：「溫度是自然語言處理模型中的參數，用於增加或減少模型對其最可能的反應的『信心』。較高的溫度使模型更有『創造性』，這在生成文章等方面可能很有用。較低的溫度使模型更加『自信』，這在回答問題等應用中很有用。」<ref>[https://lukesalamone.github.io/posts/what-is-temperature/ What is Temperature in NLP?🐭 :: Luke Salamone's Blog]</ref> ([https://news.ycombinator.com/item?id=35131112 <ins style="font-weight: bold; text-decoration: none;">Discussion on Hacker News</ins>])</div></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== 延伸閱讀 ==</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== 延伸閱讀 ==</div></td></tr>
</table>
Planetoid
https://wiki.planetoid.info/index.php?title=Generative_AI_glossary&diff=26270&oldid=prev
Planetoid: /* R */
2026-03-15T01:57:38Z
<p><span class="autocomment">R</span></p>
<table style="background-color: #fff; color: #202122;" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="en">
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td>
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 09:57, 15 March 2026</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l21">Line 21:</td>
<td colspan="2" class="diff-lineno">Line 21:</td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== R ==</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== R ==</div></td></tr>
<tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>* RAG (Retrieval-augmented generation，檢索增強生成)：「檢索增強生成（英語：Retrieval-augmented generation，RAG）是一種使大語言模型（LLM）能夠從外部資料來源中檢索並整合新資訊的技術。」(資料來源：[https://zh.wikipedia.org/zh-tw/%E6%AA%A2%E7%B4%A2%E5%A2%9E%E5%BC%B7%E7%94%9F%E6%88%90 維基百科])</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>* RAG (Retrieval-augmented generation，檢索增強生成)：「檢索增強生成（英語：Retrieval-augmented generation，RAG）是一種使大語言模型（LLM）能夠從外部資料來源中檢索並整合新資訊的技術。」(資料來源：[https://zh.wikipedia.org/zh-tw/%E6%AA%A2%E7%B4%A2%E5%A2%9E%E5%BC%B7%E7%94%9F%E6%88%90 維基百科])<ins style="font-weight: bold; text-decoration: none;"><ref>[https://medium.com/@planetoid/%E4%B8%80%E7%AF%87%E5%81%87%E6%96%87%E7%AB%A0-%E8%AE%93-google-%E5%92%8C-chatgpt-%E4%BF%A1%E4%BB%A5%E7%82%BA%E7%9C%9F-e3f7653dd6fc 一篇假文章，讓 Google 和 ChatGPT 信以為真]</ref></ins></div></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== S ==</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== S ==</div></td></tr>
</table>
Planetoid
https://wiki.planetoid.info/index.php?title=Generative_AI_glossary&diff=26269&oldid=prev
Planetoid: /* P */
2026-03-15T01:56:53Z
<p><span class="autocomment">P</span></p>
<table style="background-color: #fff; color: #202122;" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="en">
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td>
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 09:56, 15 March 2026</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l19">Line 19:</td>
<td colspan="2" class="diff-lineno">Line 19:</td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* prompt engineering (提示工程)：「提示工程」是反覆迭代的過程，透過撰寫提示詞 (prompt) 並評估模型的生成結果，來獲得您想要的結果。寫結構良好的提示是確保大型語言模型提供準確、高品質的關鍵。以下是幾種可用於最佳化生成結果的常見技巧：(1) 零樣本提示（Zero-shot prompting）：在不提供任何範例的情況下提示詞，完全依賴模型既有的知識。(2) 單一樣本提示（One-shot prompting）：在提示詞中提供一個範例，引導模型的回覆方向。(3) 少數樣本提示（Few-shot prompting）：在提示詞中提供多個範例，以符合您要求的模式或任務。」(Google, n.d.<ref>[https://docs.cloud.google.com/docs/generative-ai/glossary Generative AI glossary | Google Cloud Documentation]</ref><ref>[https://medium.com/@planetoid/%E7%99%BD%E8%A9%B1%E9%80%9A%E4%BF%97%E8%A7%A3%E9%87%8B-zero-shot-one-shot-few-shot-learning-68c56eca12ae 白話通俗解釋 zero-shot, one-shot, few-shot learning]</ref>)</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* prompt engineering (提示工程)：「提示工程」是反覆迭代的過程，透過撰寫提示詞 (prompt) 並評估模型的生成結果，來獲得您想要的結果。寫結構良好的提示是確保大型語言模型提供準確、高品質的關鍵。以下是幾種可用於最佳化生成結果的常見技巧：(1) 零樣本提示（Zero-shot prompting）：在不提供任何範例的情況下提示詞，完全依賴模型既有的知識。(2) 單一樣本提示（One-shot prompting）：在提示詞中提供一個範例，引導模型的回覆方向。(3) 少數樣本提示（Few-shot prompting）：在提示詞中提供多個範例，以符合您要求的模式或任務。」(Google, n.d.<ref>[https://docs.cloud.google.com/docs/generative-ai/glossary Generative AI glossary | Google Cloud Documentation]</ref><ref>[https://medium.com/@planetoid/%E7%99%BD%E8%A9%B1%E9%80%9A%E4%BF%97%E8%A7%A3%E9%87%8B-zero-shot-one-shot-few-shot-learning-68c56eca12ae 白話通俗解釋 zero-shot, one-shot, few-shot learning]</ref>)</div></td></tr>
<tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;"></ins></div></td></tr>
<tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">== R ==</ins></div></td></tr>
<tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">* RAG (Retrieval-augmented generation，檢索增強生成)：「檢索增強生成（英語：Retrieval-augmented generation，RAG）是一種使大語言模型（LLM）能夠從外部資料來源中檢索並整合新資訊的技術。」(資料來源：[https://zh.wikipedia.org/zh-tw/%E6%AA%A2%E7%B4%A2%E5%A2%9E%E5%BC%B7%E7%94%9F%E6%88%90 維基百科])</ins></div></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== S ==</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== S ==</div></td></tr>
</table>
Planetoid
https://wiki.planetoid.info/index.php?title=Generative_AI_glossary&diff=26236&oldid=prev
Planetoid: /* P */
2026-02-17T14:22:38Z
<p><span class="autocomment">P</span></p>
<table style="background-color: #fff; color: #202122;" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="en">
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td>
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 22:22, 17 February 2026</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l16">Line 16:</td>
<td colspan="2" class="diff-lineno">Line 16:</td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== P ==</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== P ==</div></td></tr>
<tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>* <del style="font-weight: bold; text-decoration: none;">Pretraining（預訓練）：「在機器學習模型正式針對特定任務進行微調之前，先以大規模、通用型資料集進行初始訓練的過程。」</del>(moveworks, n.d.<ref>[https://www.moveworks.com/us/en/resources/ai-terms-glossary/pre-training What is Pre-Training?]</ref><ref>[https://www.databricks.com/blog/llm-pre-training-and-custom-llms Understanding LLM Pre-Training and Custom LLMs | Databricks Blog]</ref>)</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>* <ins style="font-weight: bold; text-decoration: none;">Pretraining (預訓練)：「在機器學習模型正式針對特定任務進行微調之前，先以大規模、通用型資料集進行初始訓練的過程。」</ins>(moveworks, n.d.<ref>[https://www.moveworks.com/us/en/resources/ai-terms-glossary/pre-training What is Pre-Training?]</ref><ref>[https://www.databricks.com/blog/llm-pre-training-and-custom-llms Understanding LLM Pre-Training and Custom LLMs | Databricks Blog<ins style="font-weight: bold; text-decoration: none;">]</ref>)</ins></div></td></tr>
<tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div> </div></td></tr>
<tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">* prompt engineering (提示工程)：「提示工程」是反覆迭代的過程，透過撰寫提示詞 (prompt) 並評估模型的生成結果，來獲得您想要的結果。寫結構良好的提示是確保大型語言模型提供準確、高品質的關鍵。以下是幾種可用於最佳化生成結果的常見技巧：(1) 零樣本提示（Zero-shot prompting）：在不提供任何範例的情況下提示詞，完全依賴模型既有的知識。(2) 單一樣本提示（One-shot prompting）：在提示詞中提供一個範例，引導模型的回覆方向。(3) 少數樣本提示（Few-shot prompting）：在提示詞中提供多個範例，以符合您要求的模式或任務。」(Google, n.d.<ref>[https://docs.cloud.google.com/docs/generative-ai/glossary Generative AI glossary | Google Cloud Documentation]</ref><ref>[https://medium.com/@planetoid/%E7%99%BD%E8%A9%B1%E9%80%9A%E4%BF%97%E8%A7%A3%E9%87%8B-zero-shot-one-shot-few-shot-learning-68c56eca12ae 白話通俗解釋 zero-shot, one-shot, few-shot learning</ins>]</ref>)</div></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== S ==</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== S ==</div></td></tr>
</table>
Planetoid
https://wiki.planetoid.info/index.php?title=Generative_AI_glossary&diff=26235&oldid=prev
Planetoid: /* 延伸閱讀 */
2026-02-17T14:02:36Z
<p><span class="autocomment">延伸閱讀</span></p>
<table style="background-color: #fff; color: #202122;" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="en">
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td>
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 22:02, 17 February 2026</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l26">Line 26:</td>
<td colspan="2" class="diff-lineno">Line 26:</td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== 延伸閱讀 ==</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== 延伸閱讀 ==</div></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div># [https://blog.hlb.im/generative-ai-openai-%E8%A9%9E%E5%BD%99%E5%B0%8D%E7%85%A7%E8%A1%A8-591d2a1f1612 Generative AI / OpenAI 詞彙對照表. 本篇文章提供 Generative AI 領域常用的詞彙對照表，內容翻譯自… | by Liang-Bin Hsueh aka hlb | Medium]</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div># [https://blog.hlb.im/generative-ai-openai-%E8%A9%9E%E5%BD%99%E5%B0%8D%E7%85%A7%E8%A1%A8-591d2a1f1612 Generative AI / OpenAI 詞彙對照表. 本篇文章提供 Generative AI 領域常用的詞彙對照表，內容翻譯自… | by Liang-Bin Hsueh aka hlb | Medium]</div></td></tr>
<tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;"># [https://docs.cloud.google.com/docs/generative-ai/glossary Generative AI glossary | Google Cloud Documentation]</ins></div></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== 參考資料 ==</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== 參考資料 ==</div></td></tr>
</table>
Planetoid
https://wiki.planetoid.info/index.php?title=Generative_AI_glossary&diff=26231&oldid=prev
Planetoid: /* P */
2026-02-17T13:59:23Z
<p><span class="autocomment">P</span></p>
<table style="background-color: #fff; color: #202122;" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="en">
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td>
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 21:59, 17 February 2026</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l16">Line 16:</td>
<td colspan="2" class="diff-lineno">Line 16:</td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== P ==</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== P ==</div></td></tr>
<tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>* Pretraining（預訓練）：「在機器學習模型正式針對特定任務進行微調之前，先以大規模、通用型資料集進行初始訓練的過程。」(moveworks, n.d.<ref>[https://www.moveworks.com/us/en/resources/ai-terms-glossary/pre-training What is Pre-Training?]</ref>)</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>* Pretraining（預訓練）：「在機器學習模型正式針對特定任務進行微調之前，先以大規模、通用型資料集進行初始訓練的過程。」(moveworks, n.d.<ref>[https://www.moveworks.com/us/en/resources/ai-terms-glossary/pre-training What is Pre-Training?<ins style="font-weight: bold; text-decoration: none;">]</ref><ref>[https://www.databricks.com/blog/llm-pre-training-and-custom-llms Understanding LLM Pre-Training and Custom LLMs | Databricks Blog</ins>]</ref>)</div></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== S ==</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== S ==</div></td></tr>
</table>
Planetoid