RRepoGEO

REPOGEO REPORT · LITE

HKUDS/LLMRec

Default branch main · commit 169f3614 · scanned 6/12/2026, 9:13:02 PM

GitHub: 529 stars · 70 forks

AI VISIBILITY SCORE
40 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
2 pass · 0 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 HKUDS/LLMRec, 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
  • highreadme#1
    Reposition README opening to clarify its role as a framework and benchmark

    Why:

    CURRENT
    LLMRec is a novel framework that enhances recommenders by applying three simple yet effective LLM-based graph augmentation strategies to recommendation system.
    COPY-PASTE FIX
    LLMRec is a novel framework that enhances recommenders by applying three simple yet effective LLM-based graph augmentation strategies to recommendation system. It serves as a comprehensive and reproducible benchmark suite for evaluating various LLM-based recommendation models.
  • mediumhomepage#2
    Update the repository's homepage URL to the project website

    Why:

    CURRENT
    https://arxiv.org/abs/2311.00423
    COPY-PASTE FIX
    https://llmrec.github.io/
  • lowtopics#3
    Add specific topics related to benchmarking and evaluation for LLM-based recommendation

    Why:

    CURRENT
    colloborative-filtering, content-based-recommendation, data-augmentation-strategies, graph-augmentation, graph-learning, multi-modal-recommendation, recommendation-system, recommendation-with-side-information
    COPY-PASTE FIX
    colloborative-filtering, content-based-recommendation, data-augmentation-strategies, graph-augmentation, graph-learning, multi-modal-recommendation, recommendation-system, recommendation-with-side-information, llm-recommendation-benchmark, recommendation-evaluation

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 HKUDS/LLMRec
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 3 of 2 queries
COMPETITOR LEADERBOARD
  1. Hugging Face Transformers · recommended 3×
  2. BERT · recommended 2×
  3. RoBERTa · recommended 2×
  4. RDFLib · recommended 2×
  5. spaCy · recommended 2×
  • CATEGORY QUERY
    How can I enhance recommendation system performance using large language models with graph data?
    you: not recommended
    AI recommended (in order):
    1. PyTorch Geometric (PyG)
    2. Deep Graph Library (DGL)
    3. Hugging Face Transformers
    4. BERT
    5. RoBERTa
    6. MPNet
    7. Sentence-BERT
    8. OpenAI API (GPT-3.5, GPT-4)
    9. Anthropic Claude (Claude 2, Claude 3)
    10. Llama 2 / Llama 3
    11. Surprise
    12. LightFM
    13. Scikit-learn
    14. Grakn (now TypeDB)
    15. Neo4j
    16. RDFLib

    AI recommended 16 alternatives but never named HKUDS/LLMRec. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What are effective data augmentation strategies for recommendation graphs leveraging natural language content?
    you: not recommended
    AI recommended (in order):
    1. Google Cloud Translation API
    2. DeepL API
    3. spaCy
    4. WordNet
    5. Word2Vec
    6. GloVe
    7. Gensim
    8. Hugging Face Transformers
    9. Hugging Face Transformers
    10. BERT
    11. RoBERTa
    12. T5
    13. OpenNMT
    14. Fairseq
    15. T5
    16. GPT-2/GPT-3
    17. OpenAI API
    18. NLTK
    19. spaCy
    20. TextAttack
    21. DBpedia
    22. Wikidata
    23. RDFLib

    AI recommended 23 alternatives but never named HKUDS/LLMRec. This is the gap to close.

    Show full AI answer

Objective checks

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

  • Metadata completeness
    pass

  • 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 HKUDS/LLMRec?
    pass
    AI named HKUDS/LLMRec explicitly

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

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

Subscribe to Pro for deep diagnoses

HKUDS/LLMRec — 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