flora0110
    • Create new note
    • Create a note from template
      • Sharing URL Link copied
      • /edit
      • View mode
        • Edit mode
        • View mode
        • Book mode
        • Slide mode
        Edit mode View mode Book mode Slide mode
      • Customize slides
      • Note Permission
      • Read
        • Only me
        • Signed-in users
        • Everyone
        Only me Signed-in users Everyone
      • Write
        • Only me
        • Signed-in users
        • Everyone
        Only me Signed-in users Everyone
      • Engagement control Commenting, Suggest edit, Emoji Reply
    • Invite by email
      Invitee

      This note has no invitees

    • Publish Note

      Share your work with the world Congratulations! 🎉 Your note is out in the world Publish Note

      Your note will be visible on your profile and discoverable by anyone.
      Your note is now live.
      This note is visible on your profile and discoverable online.
      Everyone on the web can find and read all notes of this public team.
      See published notes
      Unpublish note
      Please check the box to agree to the Community Guidelines.
      View profile
    • Commenting
      Permission
      Disabled Forbidden Owners Signed-in users Everyone
    • Enable
    • Permission
      • Forbidden
      • Owners
      • Signed-in users
      • Everyone
    • Suggest edit
      Permission
      Disabled Forbidden Owners Signed-in users Everyone
    • Enable
    • Permission
      • Forbidden
      • Owners
      • Signed-in users
    • Emoji Reply
    • Enable
    • Versions and GitHub Sync
    • Note settings
    • Note Insights New
    • Engagement control
    • Make a copy
    • Transfer ownership
    • Delete this note
    • Save as template
    • Insert from template
    • Import from
      • Dropbox
      • Google Drive
      • Gist
      • Clipboard
    • Export to
      • Dropbox
      • Google Drive
      • Gist
    • Download
      • Markdown
      • HTML
      • Raw HTML
Menu Note settings Note Insights Versions and GitHub Sync Sharing URL Create Help
Create Create new note Create a note from template
Menu
Options
Engagement control Make a copy Transfer ownership Delete this note
Import from
Dropbox Google Drive Gist Clipboard
Export to
Dropbox Google Drive Gist
Download
Markdown HTML Raw HTML
Back
Sharing URL Link copied
/edit
View mode
  • Edit mode
  • View mode
  • Book mode
  • Slide mode
Edit mode View mode Book mode Slide mode
Customize slides
Note Permission
Read
Only me
  • Only me
  • Signed-in users
  • Everyone
Only me Signed-in users Everyone
Write
Only me
  • Only me
  • Signed-in users
  • Everyone
Only me Signed-in users Everyone
Engagement control Commenting, Suggest edit, Emoji Reply
  • Invite by email
    Invitee

    This note has no invitees

  • Publish Note

    Share your work with the world Congratulations! 🎉 Your note is out in the world Publish Note

    Your note will be visible on your profile and discoverable by anyone.
    Your note is now live.
    This note is visible on your profile and discoverable online.
    Everyone on the web can find and read all notes of this public team.
    See published notes
    Unpublish note
    Please check the box to agree to the Community Guidelines.
    View profile
    Engagement control
    Commenting
    Permission
    Disabled Forbidden Owners Signed-in users Everyone
    Enable
    Permission
    • Forbidden
    • Owners
    • Signed-in users
    • Everyone
    Suggest edit
    Permission
    Disabled Forbidden Owners Signed-in users Everyone
    Enable
    Permission
    • Forbidden
    • Owners
    • Signed-in users
    Emoji Reply
    Enable
    Import from Dropbox Google Drive Gist Clipboard
       Owned this note    Owned this note      
    Published Linked with GitHub
    • Any changes
      Be notified of any changes
    • Mention me
      Be notified of mention me
    • Unsubscribe
    implicit factors retrieve 6/26 === 原方法 --- ### 1. **對兩篇判決書$(c_i, c_{\lambda})$做因素($f_{(i, \lambda),j}$)和判決書說明($e_i$, $e_\lambda$)萃取**: 對於每個案件對 $(c_i, c_{\lambda})$,使用 LLM 生成因素和判決書說明集合 $y_{(i, \lambda)} = \{(f_{(i, \lambda),j}, e_{i,j}, e_{\lambda,j})\}$: $$ y_{(i, \lambda)} = P(y \mid c_i, c_{\lambda}, p_{\text{SSR}}) $$ $f_{(i, \lambda),j}$表示從兩篇判決書$(c_i, c_{\lambda})$ 提取出的第$j$個因素,兩個判決書也都會針對這個因素($f_{(i, \lambda),j}$)給出對應的說明($e_{i,j}$, $e_{\lambda,j}$) $p_{\text{SSR}}$ = `f"我會給你一篇判決書的理由內容,理由內容為法官對「為何做出這樣的判定結果」的解釋。你的任務是根據理由內容,列出影響判決的因素並詳細說明,輸出格式請以「因素一:說明、因素二:說明...」呈現。注意,不要直接輸出人名,以被害人、被告、原告等代替。\n理由內容如下:{data}\n輸出:"` ### 2. **判決書說明($e_i, e_\lambda$)用 K-means 分10群**: 1. 先把所有因素集合在一起 $$ F = \sum_{i,\lambda} \sum_j {f_{(i, \lambda), j}} $$ 2. 將因素集合 $\mathbf{F}$ 表示為高維度向量 $\mathbf{V} \subset \mathbb{R}^h$。使用 K-means 聚類算法將這些向量分成 $n=10$ 個群,最小化群內平方和(WCSS): $$ \text{WCSS} = \sum_{j=1}^{10} \sum_{\mathbf{v}_i \in C_j} \|\mathbf{v}_i - \mathbf{\mu}_j\|^2 $$ 其中,$C_j$ 表示第 $j$ 個群,$\mathbf{\mu}_j$ 是第 $j$ 個群的質心: $$ \mathbf{\mu}_j = \frac{1}{|C_j|} \sum_{\mathbf{v}_i \in C_j} \mathbf{v}_i $$ 3. 將同一群的因素($f_j$)對應的判決書說明($e$)整理在一起 $$ E_j = \{e_i \mid \mathbf{v}_i \in C_j\} $$ ==總共有10群($0 \leq j \leq 10$)== ### 3. **判決書說明壓縮**: $$ \hat{E}_j = \text{Compress}(\{E_j\}) $$ ==總共有10群($0 \leq j \leq 10$)== ### 4. **細項因素($a_k$)萃取**: 使用 LLM 從每個判決書說明集合 $\hat{E}_j$ 中萃取細項因素: $$ \{a_{j,k}\} = P(a \mid \hat{E}_j, p_{\text{TF}}) $$ 其中,$a_{j,k}$ 表示從解釋集合 $E_j$ 中萃取出的細項因素。 $p_{\text{TF}}$ = f"我會給你兩個判決書說明,判決書說明內容為針對量刑因子「{群名}」的解釋。請據判決書說明一及判決書說明二的內容差異列點列出影響不同判決的因素(請給出以“是否”為開頭之問句):" ==這只會做10次細項因素($a_k$)萃取,細項因素($\{a_{j,k}\}$)會有10群(大概是120個左右)== ### 5. **細項因素壓縮**: 先把所有細項因素集合在一起 $$ A = \sum_j^{10} \{a_{j,k}\} $$ 然後再進行壓縮 $$ \hat{A} = \text{Compress}(A) $$ ==從120個左右的細項因素萃取出20個== 6/23 老師修改後的方法 --- ### 1. **對兩篇判決書$(c_i, c_{\lambda})$做因素($f_{(i, \lambda),j}$)和判決書說明($e_i$, $e_\lambda$)萃取**: 對於每個案件對 $(c_i, c_{\lambda})$,使用 LLM 生成因素和判決書說明集合 $y_{(i, \lambda)} = \{(f_{(i, \lambda),j}, e_{i,j}, e_{\lambda,j})\}$: $$ y_{(i, \lambda)} = P(y \mid c_i, c_{\lambda}, p_{\text{SSR}}) $$ $f_{(i, \lambda),j}$表示從兩篇判決書$(c_i, c_{\lambda})$ 提取出的第$j$個因素,兩個判決書也都會針對這個因素($f_{(i, \lambda),j}$)給出對應的說明($e_{i,j}$, $e_{\lambda,j}$) $p_{\text{SSR}}$ = f"我會給你一篇判決書的理由內容,理由內容為法官對「為何做出這樣的判定結果」的解釋。你的任務是根據理由內容,列出影響判決的因素並詳細說明,輸出格式請以「因素一:說明、因素二:說明...」呈現。注意,不要直接輸出人名,以被害人、被告、原告等代替。\n理由內容如下:{data}\n輸出:" ### 2. **判決書說明壓縮**: 先把所有判決書說明集合在一起 $$ E = \sum_{i, \lambda} \sum_j e_{i,j}, e_{\lambda,j} $$ 然後再進行壓縮 $$ \hat{E} = \text{Compress}(E) $$ ==因為沒有做將**同一群的因素($f_{(i, \lambda)}$)對應的判決書說明($e_i$, $e_\lambda$)整理在一起,然後再對每個群分別進行壓縮**,所以$\hat{E}$只有一群== ### 3. **細項因素($a_k$)萃取**: 使用 LLM 從判決書說明集合 $\{e_j\}$ 中萃取細項因素: $$ \{a_{k}\} = P(a \mid \{e_j\}, p_{\text{TF}}) $$ 其中,$\{a_{k}\}$ 表示從解釋集合 $\{e_j\}$ 中萃取出的細項因素。 $p_{\text{TF}}$ = f"我會給你兩個判決書說明,判決書說明內容為針對量刑因子「{群名}」的解釋。請據判決書說明一及判決書說明二的內容差異列點列出影響不同判決的因素(請給出以“是否”為開頭之問句):" ==因為上一步只有一群($\hat{E}$),所以這邊只會做一次細項因素($a_k$)萃取,細項因素($\{a_{k}\}$)也只會有一群(大概是12個左右)== ### 4. **細項因素壓縮**: $$ \hat{a}_{j,m} = \text{Compress}(\{a_{k}\}) $$ ==因為上一步只有12個左右的細項因素,最後會只是從12個細項因素萃取出10個== 修改方法(不用因素($f$)分群,用判決書說明($e$)分群) --- ### 1. **對兩篇判決書$(c_i, c_{\lambda})$做因素($f_{(i, \lambda),j}$)和判決書說明($e_i$, $e_\lambda$)萃取**: 對於每個案件對 $(c_i, c_{\lambda})$,使用 LLM 生成因素和判決書說明集合 $y_{(i, \lambda)} = \{(f_{(i, \lambda),j}, e_{i,j}, e_{\lambda,j})\}$: $$ y_{(i, \lambda)} = P(y \mid c_i, c_{\lambda}, p_{\text{SSR}}) $$ $f_{(i, \lambda),j}$表示從兩篇判決書$(c_i, c_{\lambda})$ 提取出的第$j$個因素,兩個判決書也都會針對這個因素($f_{(i, \lambda),j}$)給出對應的說明($e_{i,j}$, $e_{\lambda,j}$) $p_{\text{SSR}}$ = f"我會給你一篇判決書的理由內容,理由內容為法官對「為何做出這樣的判定結果」的解釋。你的任務是根據理由內容,列出影響判決的因素並詳細說明,輸出格式請以「因素一:說明、因素二:說明...」呈現。注意,不要直接輸出人名,以被害人、被告、原告等代替。\n理由內容如下:{data}\n輸出:" ### 2. **判決書說明($e$)分群**: 1. 先把所有判決書說明集合在一起 $$ E = \sum_{i, \lambda} \sum_j e_{i,j}, e_{\lambda,j} $$ 2. 將判決書集合 $\mathbf{E}$ 表示為高維度向量 $\mathbf{V} \subset \mathbb{R}^h$。使用 K-means 聚類算法將這些向量分成 $n=10$ 個群,最小化群內平方和(WCSS): $$ \text{WCSS} = \sum_{j=1}^{10} \sum_{\mathbf{v}_i \in C_j} \|\mathbf{v}_i - \mathbf{\mu}_j\|^2 $$ 其中,$C_j$ 表示第 $j$ 個群,$\mathbf{\mu}_j$ 是第 $j$ 個群的質心: $$ \mathbf{\mu}_j = \frac{1}{|C_j|} \sum_{\mathbf{v}_i \in C_j} \mathbf{v}_i $$ 3. 將同一群的因素($f_j$)對應的判決書說明($e$)整理在一起 $$ E_j = \{e_i \mid \mathbf{v}_i \in C_j\} $$ ==總共有10群($0 \leq j \leq 10$)== ### 3. **判決書說明壓縮**: $$ \hat{E}_j = \text{Compress}(\{E_j\}) $$ ==總共有10群($0 \leq j \leq 10$)== ### 4. **細項因素($a_k$)萃取**: 使用 LLM 從每個判決書說明集合 $\hat{E}_j$ 中萃取細項因素: $$ \{a_{j,k}\} = P(a \mid \hat{E}_j, p_{\text{TF}}) $$ 其中,$a_{j,k}$ 表示從解釋集合 $E_j$ 中萃取出的細項因素。 $p_{\text{TF}}$ = f"我會給你兩個判決書說明,判決書說明內容為針對量刑因子「{群名}」的解釋。請據判決書說明一及判決書說明二的內容差異列點列出影響不同判決的因素(請給出以“是否”為開頭之問句):" ==這只會做10次細項因素($a_k$)萃取,細項因素($\{a_{j,k}\}$)會有10群(大概是120個左右)== ### 5. **細項因素壓縮**: 先把所有細項因素集合在一起 $$ A = \sum_j^{10} \{a_{j,k}\} $$ 然後再進行壓縮 $$ \hat{A} = \text{Compress}(A) $$ ==從120個左右的細項因素萃取出20個== 壓縮方法 $Compress$ --- **1. 分群** 將每個要被壓縮的實體($\mathbf{e}_i$) 表示為高維度向量 $\mathbf{v}_i \in \mathbb{R}^h$。使用 K-means 聚類算法將這些向量分成 $num=10$ 個群,最小化群內平方和(WCSS): $$ \text{WCSS} = \sum_{j=1}^{10} \sum_{\mathbf{v}_i \in C_j} \|\mathbf{v}_i - \mathbf{\mu}_j\|^2 $$ 其中,$C_j$ 表示第 $j$ 個群,$\mathbf{\mu}_j$ 是第 $j$ 個群的質心: $$ \mathbf{\mu}_j = \frac{1}{|C_j|} \sum_{\mathbf{v}_i \in C_j} \mathbf{v}_i $$ $$ E_j = \{e_i \mid \mathbf{v}_i \in C_j\} $$ **2. 隨機抽取** 從集合 $E_j$ 中隨機選擇一個或多個(這邊先預設一個)實體 $\mathbf{e}_k$ 作為該群的代表: $$ {e_k} \in E_j $$ 最後會$e_i$壓縮成$num=10$個

    Import from clipboard

    Paste your markdown or webpage here...

    Advanced permission required

    Your current role can only read. Ask the system administrator to acquire write and comment permission.

    This team is disabled

    Sorry, this team is disabled. You can't edit this note.

    This note is locked

    Sorry, only owner can edit this note.

    Reach the limit

    Sorry, you've reached the max length this note can be.
    Please reduce the content or divide it to more notes, thank you!

    Import from Gist

    Import from Snippet

    or

    Export to Snippet

    Are you sure?

    Do you really want to delete this note?
    All users will lose their connection.

    Create a note from template

    Create a note from template

    Oops...
    This template has been removed or transferred.
    Upgrade
    All
    • All
    • Team
    No template.

    Create a template

    Upgrade

    Delete template

    Do you really want to delete this template?
    Turn this template into a regular note and keep its content, versions, and comments.

    This page need refresh

    You have an incompatible client version.
    Refresh to update.
    New version available!
    See releases notes here
    Refresh to enjoy new features.
    Your user state has changed.
    Refresh to load new user state.

    Sign in

    Forgot password

    or

    By clicking below, you agree to our terms of service.

    Sign in via Facebook Sign in via Twitter Sign in via GitHub Sign in via Dropbox Sign in with Wallet
    Wallet ( )
    Connect another wallet

    New to HackMD? Sign up

    Help

    • English
    • 中文
    • Français
    • Deutsch
    • 日本語
    • Español
    • Català
    • Ελληνικά
    • Português
    • italiano
    • Türkçe
    • Русский
    • Nederlands
    • hrvatski jezik
    • język polski
    • Українська
    • हिन्दी
    • svenska
    • Esperanto
    • dansk

    Documents

    Help & Tutorial

    How to use Book mode

    Slide Example

    API Docs

    Edit in VSCode

    Install browser extension

    Contacts

    Feedback

    Discord

    Send us email

    Resources

    Releases

    Pricing

    Blog

    Policy

    Terms

    Privacy

    Cheatsheet

    Syntax Example Reference
    # Header Header 基本排版
    - Unordered List
    • Unordered List
    1. Ordered List
    1. Ordered List
    - [ ] Todo List
    • Todo List
    > Blockquote
    Blockquote
    **Bold font** Bold font
    *Italics font* Italics font
    ~~Strikethrough~~ Strikethrough
    19^th^ 19th
    H~2~O H2O
    ++Inserted text++ Inserted text
    ==Marked text== Marked text
    [link text](https:// "title") Link
    ![image alt](https:// "title") Image
    `Code` Code 在筆記中貼入程式碼
    ```javascript
    var i = 0;
    ```
    var i = 0;
    :smile: :smile: Emoji list
    {%youtube youtube_id %} Externals
    $L^aT_eX$ LaTeX
    :::info
    This is a alert area.
    :::

    This is a alert area.

    Versions and GitHub Sync
    Get Full History Access

    • Edit version name
    • Delete

    revision author avatar     named on  

    More Less

    Note content is identical to the latest version.
    Compare
      Choose a version
      No search result
      Version not found
    Sign in to link this note to GitHub
    Learn more
    This note is not linked with GitHub
     

    Feedback

    Submission failed, please try again

    Thanks for your support.

    On a scale of 0-10, how likely is it that you would recommend HackMD to your friends, family or business associates?

    Please give us some advice and help us improve HackMD.

     

    Thanks for your feedback

    Remove version name

    Do you want to remove this version name and description?

    Transfer ownership

    Transfer to
      Warning: is a public team. If you transfer note to this team, everyone on the web can find and read this note.

        Link with GitHub

        Please authorize HackMD on GitHub
        • Please sign in to GitHub and install the HackMD app on your GitHub repo.
        • HackMD links with GitHub through a GitHub App. You can choose which repo to install our App.
        Learn more  Sign in to GitHub

        Push the note to GitHub Push to GitHub Pull a file from GitHub

          Authorize again
         

        Choose which file to push to

        Select repo
        Refresh Authorize more repos
        Select branch
        Select file
        Select branch
        Choose version(s) to push
        • Save a new version and push
        • Choose from existing versions
        Include title and tags
        Available push count

        Pull from GitHub

         
        File from GitHub
        File from HackMD

        GitHub Link Settings

        File linked

        Linked by
        File path
        Last synced branch
        Available push count

        Danger Zone

        Unlink
        You will no longer receive notification when GitHub file changes after unlink.

        Syncing

        Push failed

        Push successfully