RRepoGEO

REPOGEO REPORT · LITE

google-research/distilling-step-by-step

Default branch main · commit ef944263 · scanned 6/4/2026, 11:43:11 PM

GitHub: 592 stars · 100 forks

AI VISIBILITY SCORE
23 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
1 pass · 0 warn · 1 fail
Objective metadata checks
AI knows your name
2 / 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 google-research/distilling-step-by-step, 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

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

OVERALL DIRECTION
  • highreadme#1
    Reposition the README's opening to clearly state the project's core purpose and category.

    Why:

    CURRENT
    # Distilling Step-by-Step!

Code for paper Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes
    COPY-PASTE FIX
    # Distilling Step-by-Step!

This repository provides code for 'Distilling Step-by-Step!', a research project focused on distilling complex, multi-step reasoning (Chain-of-Thought) from larger language models (LLMs) into smaller, more efficient student models. It enables smaller LLMs to achieve superior performance with less training data by learning the reasoning processes of larger teacher models.
  • highabout#2
    Add a concise project description to the repository's 'About' section.

    Why:

    COPY-PASTE FIX
    Code for 'Distilling Step-by-Step!', a method to distill multi-step reasoning from large language models (LLMs) into smaller, more efficient student models.

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 google-research/distilling-step-by-step
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Hugging Face Optimum
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. Hugging Face Optimum · recommended 1×
  2. ONNX Runtime · recommended 1×
  3. Intel Neural Compressor · recommended 1×
  4. PyTorch Quantization · recommended 1×
  5. TensorFlow Lite · recommended 1×
  • CATEGORY QUERY
    How can I reduce the size and training data requirements for large language models?
    you: not recommended
    AI recommended (in order):
    1. Hugging Face Optimum
    2. ONNX Runtime
    3. Intel Neural Compressor
    4. PyTorch Quantization
    5. TensorFlow Lite
    6. PyTorch Pruning
    7. TensorFlow Model Optimization Toolkit
    8. Hugging Face `transformers`
    9. DistilBERT
    10. TextAttack
    11. OpenNMT
    12. Hugging Face PEFT Library
    13. LoRA
    14. TinyLlama
    15. Phi-2
    16. Gemma
    17. MobileBERT
    18. cleanlab
    19. Snorkel
    20. AugLy

    AI recommended 20 alternatives but never named google-research/distilling-step-by-step. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What techniques exist to improve smaller language model performance using knowledge distillation?
    you: not recommended
    AI recommended (in order):
    1. FitNets
    2. TinyBERT

    AI recommended 2 alternatives but never named google-research/distilling-step-by-step. This is the gap to close.

    Show full AI answer

Objective checks

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

  • Metadata completeness
    fail

    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 google-research/distilling-step-by-step?
    pass
    AI named google-research/distilling-step-by-step explicitly

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

  • If a team adopts google-research/distilling-step-by-step in production, what risks or prerequisites should they evaluate first?
    pass
    AI named google-research/distilling-step-by-step 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 google-research/distilling-step-by-step solve, and who is the primary audience?
    pass
    AI did not name google-research/distilling-step-by-step — likely talking about a different project

    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 google-research/distilling-step-by-step. 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/google-research/distilling-step-by-step.svg)](https://repogeo.com/en/r/google-research/distilling-step-by-step)
HTML
<a href="https://repogeo.com/en/r/google-research/distilling-step-by-step"><img src="https://repogeo.com/badge/google-research/distilling-step-by-step.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

google-research/distilling-step-by-step — 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
google-research/distilling-step-by-step — RepoGEO report