Live data from Hacker News

Viewing profile — Xudong

Xudong

HN member
Joined
Tue, Apr 04, 2023, 9:33 AM UTC
HN karma
80
Public activity
17 items

About Xudong

No profile information was provided.

Recent public activity

  1. comment
    Comment #40563107

    Fact-checking is really hard. How do you know what sources are reliable? How to balance or compare contradict evidences? We don’t have a clear answer yet. Therefore, instead of mak…

  2. comment
    Comment #40067811

    This past week has been transformative since Loki went open source. We're thrilled by the progress and eager to share our development plan. Thanks to your input, we have enhanced t…

  3. story
  4. comment
    Comment #39956105

    I will take it as a compliment, lol. But I do hope ChatGPT or some agents could help me with this. Btw, our recent study on machine-generated text detection might be interesting to…

  5. comment
    Comment #39955020

    Thanks for your feedback on the gif figure, swores! We will revise it soon.

  6. comment
    Comment #39954999

    Hi siffland! Thank you for your feedback. We understand your concern about the potential confusion given the popularity of Grafana Loki in the logging space. When naming our projec…

  7. comment
    Comment #39954914

    Thank you for your suggestions, axegon!!! We will definitely consider them and add the features in a future version shortly. Regarding the first version, we are currently working o…

  8. comment
    Comment #39954785

    Hello vinni2, thank you for mentioning the paper. However, I noticed that it hasn't gone through peer review yet. Also, the paper suggests that fine-tuning may work better than in-…

  9. comment
    Comment #39954696

    I apologize for any confusion caused earlier. The core components have been defined separately ( https://github.com/Libr-AI/OpenFactVerification/tree/main/fa... ) to make customiza…

  10. comment
    Comment #39954646

    ahah thanks!

  11. comment
    Comment #39954634

    I wholeheartedly agree on the necessity of linking fact-checking tools to credible sources. Currently, our team's expertise lies primarily in AI, and we find ourselves at a disadva…

  12. comment
    Comment #39954536

    Yes, they are similar. Actually, our initial paper was presented around five months ago ( https://arxiv.org/abs/2311.09000 ). Unfortunately, our paper isn't cited by the DeepMind p…

  13. comment
    Comment #39954451

    Hi there, I agree that fact-checking is not something that current generative AI models can directly solve. Therefore, we decompose this complex into five simpler steps, which curr…

  14. comment
    Comment #39954376

    Hi Der_Einzige, thanks for pointing out these two great datasets! We are currently working on including customized evidence sources internally and will definitely consider these tw…

  15. comment
    Comment #39954328

    Thanks for your response. When discussing fact-checking capabilities, the key question is always: Can we guarantee that it will always offer the correct justification? While it's u…

  16. comment
    Comment #39951572

    [flagged]

  17. story