Skip to content

Results are only presented with niche LLM of doubao-1.5 #9

Open

Description

@Qingbolan

Fix LaaJ LLM model to GPT-4.1-mini, try the following possible candidates as base LLMs:

  • Qwen3: 8b, 14b, 30b-a3b
  • Gemini: 2.0-flash-lite, 2.5-flash-lite
  • repeat time: one time first for all five models, and preserve two base models (one from Qwen and one from Gemini) for repeating three times
  • datasets: first try LM-SYS-100

Activity

  1. added theissue type on Nov 13, 2025
  2. removed theissue type on Nov 13, 2025
  3. Qingbolan commented on Nov 13, 2025

    @Qingbolan
    MemberAuthor
    • Qwen3-8B and Qwen3-14B could not be included in our experiments because their context windows are too small to support the full input required by the baseline and our three proposed methods. As a result, these models cannot execute comparable runs.
  4. Qingbolan commented on Nov 13, 2025

    @Qingbolan
    MemberAuthor
    Image
  5. Qingbolan commented on Nov 13, 2025

    @Qingbolan
    MemberAuthor
    Image
  6. Qingbolan commented on Nov 13, 2025

    @Qingbolan
    MemberAuthor
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    llm-eval-more-modelsResults are only presented with niche LLM doubao-1.5rebuttlerebuttle of paper submit

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions