RRepoGEO

REPOGEO REPORT · LITE

nlpai-lab/KULLM

Default branch main · commit 2de1d301 · scanned 5/29/2026, 11:52:41 PM

GitHub: 586 stars · 71 forks

AI VISIBILITY SCORE
57 /100
Needs work
Category recall
1 / 2
Avg rank #5.0 when recommended
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 nlpai-lab/KULLM, 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
  • hightopics#1
    Add relevant topics to the repository

    Why:

    COPY-PASTE FIX
    korean-llm, large-language-model, llm, nlp, korean-nlp, instruction-tuning, polyglot-ko, deep-learning, machine-learning, korea-university
  • mediumreadme#2
    Strengthen the README's opening statement for clarity and differentiation

    Why:

    CURRENT
    KULLM(구름)은 고려대학교 NLP & AI 연구실과 HIAI 연구소가 개발한 한국어 Large Language Model (LLM) 입니다.
    COPY-PASTE FIX
    KULLM(구름)은 고려대학교 NLP & AI 연구실과 HIAI 연구소가 개발한, 한국어에 특화된 오픈소스 대규모 언어 모델(LLM)입니다. 특히, 한국어 지시를 따르도록 미세 조정되어 다양한 한국어 NLP 작업에 최적화되어 있습니다.
  • lowreadme#3
    Add a 'Why KULLM?' or 'Comparison' section to the README

    Why:

    COPY-PASTE FIX
    ## Why KULLM? (왜 구름인가요?)

[Add content here explaining KULLM's unique strengths, e.g., open-source nature, specific instruction-tuning, performance benchmarks, or comparison to other Korean LLMs like KoGPT or Polyglot-Ko.]

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
1 / 2
50% of queries surface nlpai-lab/KULLM
Avg rank
#5.0
Lower is better. #1 = top recommendation.
Share of voice
8%
Of all named tools, what % are you?
Top rival
HyperCLOVA X
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. HyperCLOVA X · recommended 1×
  2. GPT-4 · recommended 1×
  3. GPT-3.5 Turbo · recommended 1×
  4. CLOVA X · recommended 1×
  5. KoGPT · recommended 1×
  • CATEGORY QUERY
    What are the best large language models optimized for Korean language tasks?
    you: not recommended
    AI recommended (in order):
    1. HyperCLOVA X
    2. GPT-4
    3. GPT-3.5 Turbo
    4. CLOVA X
    5. KoGPT
    6. Polyglot-Ko
    7. Llama 2

    AI recommended 7 alternatives but never named nlpai-lab/KULLM. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Seeking an open-source large language model for high-performance Korean text generation.
    you: #5
    AI recommended (in order):
    1. Polyglot-Ko (EleutherAI/Polyglot-Ko)
    2. KoGPT (KakaoBrain/kogpt)
    3. Llama 2 (Meta/Llama-2-7b-chat-hf)
    4. SOLAR (Upstage/SOLAR-10.7B-v1.0)
    5. KULLM (nlpai-lab/kullm-v2) ← you
    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 nlpai-lab/KULLM?
    pass
    AI named nlpai-lab/KULLM explicitly

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

  • If a team adopts nlpai-lab/KULLM in production, what risks or prerequisites should they evaluate first?
    pass
    AI named nlpai-lab/KULLM 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 nlpai-lab/KULLM solve, and who is the primary audience?
    pass
    AI named nlpai-lab/KULLM 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 nlpai-lab/KULLM. 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/nlpai-lab/KULLM.svg)](https://repogeo.com/en/r/nlpai-lab/KULLM)
HTML
<a href="https://repogeo.com/en/r/nlpai-lab/KULLM"><img src="https://repogeo.com/badge/nlpai-lab/KULLM.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

nlpai-lab/KULLM — 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