Hello World Dev Conference
      • 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
        • Owners
        • Signed-in users
        • Everyone
        Owners Signed-in users Everyone
      • Write
        • Owners
        • Signed-in users
        • Everyone
        Owners 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
    • 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 Help
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
Owners
  • Owners
  • Signed-in users
  • Everyone
Owners Signed-in users Everyone
Write
Owners
  • Owners
  • Signed-in users
  • Everyone
Owners 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
    --- GA: UA-34467841-15 --- # 「我用的模型考試都考一百分」語言模型如何技術選型?內行人都這樣看模型跑分 - Summit Suen ###### tags: `HelloWorld2025` `HWDC2025` `2025` `DE 會議室` `AI 與系統架構設計` <blockquote> 介紹現行大型/多模態語言模型評測方式的目的及遇到的瓶頸,透過文獻回顧來討論從更多面向(認知、知識、公平、資安⋯⋯等)去衡量語言模型能力的思路,亦可作為開發者在選用語言模型時的技術選型階段能夠參考的指引與架構。另外也介紹實作語言模型評測資料集時會遇到的挑戰以及處理方式。 聽眾收穫: 能夠理解現行語言模型評測方式的痛點,並且開啟一個從更多面向去衡量語言模型的思路,讓開發者在選用語言模型時,有更明確的指引及架構。 </blockquote> {%hackmd @HWDC/announcement-2025 %} ## 會議資訊 **時間:** 15:10 ~ 15:40 **地點:** DE 會議室 **日期:** 2025年10月15日 **語言:** 中文 **難度:** 中階 **相關連結:** - [Hello World Dev Conference 2025 官方網站](https://hwdc.ithome.com.tw/2025) [target=_blank] - [Hello World 2025 議程表](https://hwdc.ithome.com.tw/2025/agenda) [target=_blank] ## 筆記區 ### 語言模型評測 - **傳統 ML 模型** - 解決特定問題 - 推薦系統:顧客瀏覽/購買記錄 - 文字客服:過往問答紀錄 - 手寫辨識:手寫字影像資料集 - 單一目的資料集 - 資料分割 split - 80/20: 訓練 / 測試資料 - N-fold: 避免 overfitting - 具有明確指標 - Accuracy - Confusion matrix - **LLM** - 泛用目的/訓練方法: - base model: 公開網路資料(wiki, 新聞, 論壇等) - fine-tune:自行收集整理資料 - RAG:單位內部資料(知識庫) - 廣泛用途資料集 - 再現率 vs. 準確率 - 文字輸出: free-form vs. structured - metrics: Exact Match vs. ROUGE - 本質是機率模型 - 多個指標覆蓋不同面向 - 資料如何具有代表性 評測資料集 -> 測驗題目 - 需要制定標準 - 考試 - example: [OpenVLM Leaderboard](https://huggingface.co/spaces/opencompass/open_vlm_leaderboard) - example: [Open LLM Leaderboard](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/) LLM 計分方式 - NLP way - Model way - LLM-as-a-judge - LLM Use Case - LLM system architecture ### VLM (Vision Language Model) benchmark 評測資料 - VQA - VHELM 在選模型時,判斷使用的場景,挑選相似的 benchmark,最後挑在該 benchmark 高分的模型 每個 benchmark 的目的不同 - GQA - PAIRS ### VLM benchmark 常見問題 ### 燈塔計劃 VLM benchmark 介紹 高雄燈塔計劃 ## 討論區 > 歡迎在此進行討論與 Q&A ## 相關資源 - 投影片連結:(待講者提供) - 相關文件:(待更新) ## 逐字稿 **(前面沒轉到)** 其實這些問題,就是問答這件事,其實應該是要用你的 use case 去問它,其實才會比較合乎你去使用的狀況。 對,所以就好像現在如果大家什麼Codex出來或是Caldex出來,就在大家在使用就是這些大學模型的時候比較常見的一些做法這樣。 那他跟传统,就是说传统可能也不太对,因为大规模模型这件事情其实 再去看這些不同的備忘錄。 V5N後面也是接LN,所以我這邊用V5N的評測資料來做一個大概的Benchmark現在的現況。 大概是怎麼樣子。所以比如說如果是用 Vray Benchmark 來看的話,看現在比較常就是在那個Visible 上面大家會去跑分的這些 Benchmark 到底長什麼樣子。 所以你會發現說這些Benchmark的內容其實是包容萬象,它們的任務其實是包容萬象。那通常VLM的Benchmark都是一種叫做VQN的形式,就是Vision的... 提示文章的題目就是一張圖片加一個問題,答案就是你要輸出的回答。 Benchmark 資料集就是會有標註好的回答,然後就是拿這個影像跟我的題目去問 VLM,然後看它出來的回答跟我們標註的回答的相似程度這樣。 對,那基本上不同的那個VQA或者說不同的Benchmark他們的任務其實都非常不一樣,那像這是一篇 去年2014年10月的paper他去survey就是說既有的這些AVM Benchmark他們到底cover了哪些面向然後就發現說他其實整理出來很多不同的 不同的面向就比如說有的Benchmark是針對真實世界影像的有的Benchmark是針對 手寫文字的,或者是針對一些藝術作品的,然後有些是針對...有些是有前進,有些是沒有。 所以其實就是變成說這些不同的就是Benchmark其實你如果單純就只是看他的討分你可能其實不知道他在幹嘛但是你要你是需要去知道說他背後其實 這條語音備忘錄,已進行編輯以加入正確的標點 其實你可能就不會去看這個benchmark的分數。對,就是雖然你去,你可能會看到它好像general的跑分蠻高的,但是它其實高分的那幾項其實不一定是你要的。 所以你只需要比較仔細的去看說,今天這個模型出了它在你要用的場景,比較適合的Benchmark是什麼。 然後才能去挑出比較適合你用的model。然後也會看到說其實不同的model通常它在不同的benchmark跑 因此,你很難有一個標準模式,就是所有的標準標準都超級高分,就是完全碾壓,通常不太會這樣,就是它會是某幾項比較強,某幾項比較弱。 所以我們都是可以在這些Leaderboard上面去看,就是你在挑model的時候可以從這邊去看。 它有做一些比較。然後所以這邊就剛剛講到說,其實每個Benchmark的目的寫不到。例如說,這裡有一個real-world QA,那它就是拿真實世界的影像,然後去做問答。 然後或者是另外有一個 VQA Me Too這兩種都是比較真實事件影像去做問答就是問說這張圖片裡面在講什麼可能有幾個建築物的幾個人 然後描述一下他們現在的狀況。但是也有的是說,譬如說有的benchmark是專門去做fairness的,對,就是公平性的,像這個呢,對,fairness這個右邊這一張,這個它就是 圖片裡的每個物體之間的相關性,將他們的關係建立成一個圖的概念。 ## 會後摘要 ### 視覺語言模型基準測試概述 - 視覺語言模型(VLM)評估通常採用視覺問答(VQA)形式,包含圖片、問題和預期回答 - 不同基準測試覆蓋不同面向:真實世界影像、藝術作品、手寫文字等多種類型 - 基準測試分數並非唯一選擇依據,應根據實際使用場景選擇適合的模型 - 模型通常在某些方面表現較強,某些方面較弱,很少有全面超越的模型 ### 資料集與評估挑戰 - 資料集需具備平衡性以避免模型產生偏誤(如行車影像測試中過多直線行駛場景) - GQA等基準測試專注於物體之間的關係識別能力,而非僅識別物體 - 評估方法包括自由文本比對(使用BLEU等指標)和結構化數據比對 - 信度效度評估是新興研究方向,目前發現跑分較高的模型通常信度效度也較高 ### 項目實例與應用 - 講者團隊與高雄市政府合作開發視覺語言模型應用 - 專案與NVIDIA合作,用於實時分析CCTV監控畫面 - 團隊建立自己的基準測試資料集以評估模型表現 - 目前開發的模型性能優於GPT-4o和Lambda等先進模型 ### 評估框架建議 - 評估VLM時應從多個面向考量:影像感知能力、公平性、偏見等 - 模型選擇應基於使用場景需求,而非僅看總體分數 - 資料多樣性對基準測試和模型訓練至關重要 - 目前評估多為相對性比較,尚難有絕對標準

    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