Git Product home page Git Product logo

Comments (4)

paralym avatar paralym commented on July 28, 2024

你好!

问题1.1 数据集涵盖范围

我们在当前版本文章中使用的CQIA-Subset和huggingface讨论区给出的数据一致,关于Subset的具体数据并未在初版文章中介绍,我们在完成其余实验后会一并在下一版论文中更新

问题1.2 ruozhiba的数据使用

  • ruozhiba数据构造流程是首先人工为GPT4提供弱智吧问题的逻辑缪误,然后使用GPT4生成回答框架,但该回复框架通常并不完全可用,因此我们又继续对该回复框架进行了人工修改,以达到符合SFT需求的目的。Bias的问题可能是存在的,我们仍然在进行实验来得出更严谨的结论
  • ruozhiba的数据仅有标题在最终数据集中,贴吧网友所说“你们提供了提问的思路”是正确的,因为弱智吧回复通常不适合作为SFT数据

问题1.3 baseline能力没有给出评估

我们在人工和GPT4评估中都是为了考察模型在zero-shot情况下的问答和指令遵循能力,但Yi-6B等base版本模型未经指令微调或对齐,不太适合做zero-shot设置下的问答和指令等开放生成任务,因此当时并没有考虑将其作为baseline。但我们也会尝试补充这一部分实验。对于其他baseline,我们会考虑对比同等数据量级的中文指令微调数据。

如果您仍然疑惑或者有其他问题,欢迎留言讨论!

from coig-cqia.

yata0 avatar yata0 commented on July 28, 2024

好的,非常感谢你快速的回复。想请问下一版论文有放出的时间计划吗?

from coig-cqia.

paralym avatar paralym commented on July 28, 2024

好的,非常感谢你快速的回复。想请问下一版论文有放出的时间计划吗?

下一版本尽量会在两周之内放出来

from coig-cqia.

yata0 avatar yata0 commented on July 28, 2024

好的,期待。

from coig-cqia.

Related Issues (8)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.