RRepoGEO

REPOGEO REPORT · LITE

thunlp/OPD

Default branch main · commit 1fd6cca8 · scanned 6/6/2026, 6:28:00 PM

GitHub: 602 stars · 34 forks

AI VISIBILITY SCORE
35 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
1 pass · 1 warn · 0 fail
Objective metadata checks
AI knows your name
3 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface thunlp/OPD, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • highabout#1
    Update GitHub repository description for clarity

    Why:

    CURRENT
    Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
    COPY-PASTE FIX
    Official code for 'Rethinking On-Policy Distillation of LLMs', providing techniques and insights for effective on-policy knowledge distillation.
  • highlicense#2
    Add a LICENSE file to the repository

    Why:

    COPY-PASTE FIX
    Create a `LICENSE` file in the repository root with a standard open-source license (e.g., MIT, Apache-2.0, GPL-3.0) that reflects the project's intended usage.
  • mediumabout#3
    Expand repository topics and add a homepage URL

    Why:

    CURRENT
    Topics: llms, mechanism, on-policy-distillation. Homepage: (none).
    COPY-PASTE FIX
    Update repository settings: set topics to `llms, mechanism, on-policy-distillation, knowledge-distillation, large-language-models, deep-learning, nlp, machine-learning, reinforcement-learning`. Set the homepage URL to `https://arxiv.org/abs/2604.13016`.

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
0 / 2
0% of queries surface thunlp/OPD
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Hugging Face Transformers
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. Hugging Face Transformers · recommended 1×
  2. Trainer · recommended 1×
  3. DistilBERT · recommended 1×
  4. TinyBERT · recommended 1×
  5. MiniLM · recommended 1×
  • CATEGORY QUERY
    How to efficiently distill large language models to reduce size and improve inference speed?
    you: not recommended
    AI recommended (in order):
    1. Hugging Face Transformers
    2. Trainer
    3. DistilBERT
    4. TinyBERT
    5. MiniLM
    6. OpenVINO Toolkit
    7. ONNX Runtime
    8. NVIDIA TensorRT
    9. TextBrewer
    10. bitsandbytes
    11. AutoGPTQ
    12. GPTQ

    AI recommended 12 alternatives but never named thunlp/OPD. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Seeking techniques for effective on-policy knowledge distillation in large language model applications.
    you: not recommended
    AI recommended (in order):
    1. trl library (huggingface/trl)
    2. acme (deepmind/acme)
    3. AlphaCode
    4. Constitutional AI
    5. stable-baselines3 (DLR-RM/stable-baselines3)
    6. transformers library (huggingface/transformers)

    AI recommended 6 alternatives but never named thunlp/OPD. This is the gap to close.

    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    warn

    Suggestion:

  • README presence
    pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

  • Compared to common alternatives in this category, what is the core differentiator of thunlp/OPD?
    pass
    AI named thunlp/OPD explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts thunlp/OPD in production, what risks or prerequisites should they evaluate first?
    pass
    AI named thunlp/OPD explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • In one sentence, what problem does the repo thunlp/OPD solve, and who is the primary audience?
    pass
    AI named thunlp/OPD explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of thunlp/OPD. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/thunlp/OPD.svg)](https://repogeo.com/en/r/thunlp/OPD)
HTML
<a href="https://repogeo.com/en/r/thunlp/OPD"><img src="https://repogeo.com/badge/thunlp/OPD.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

thunlp/OPD — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

  • Deep reports10 / month
  • Brand-free category queries5 vs 2 in Lite
  • Prioritized action items8 vs 3 in Lite