RRepoGEO

REPOGEO REPORT · LITE

THUDM/LongCite

Default branch main · commit d7d772e3 · scanned 6/8/2026, 2:38:12 PM

GitHub: 519 stars · 31 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 THUDM/LongCite, 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
    Add a clear introductory sentence to the README

    Why:

    COPY-PASTE FIX
    LongCite is a specialized benchmark dataset and a suite of fine-tuned LLMs designed specifically for generating accurate, fine-grained, sentence-level citations within long-context question answering, differentiating it from general LLM frameworks or retrieval systems.
  • mediumhomepage#2
    Add homepage URL to repository metadata

    Why:

    COPY-PASTE FIX
    https://arxiv.org/abs/2409.02897
  • lowtopics#3
    Add more specific topics to improve categorization

    Why:

    CURRENT
    benchmark, citation-generation, fine-tuning, llm, long-context
    COPY-PASTE FIX
    benchmark, citation-generation, fine-tuning, llm, long-context, question-answering, scientific-qa, knowledge-grounding, source-attribution, text-generation

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 THUDM/LongCite
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
OpenAI API
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. OpenAI API · recommended 2×
  2. huggingface/transformers · recommended 2×
  3. run-llama/llama_index · recommended 1×
  4. deepset-ai/haystack · recommended 1×
  5. facebookresearch/faiss · recommended 1×
  • CATEGORY QUERY
    How to improve LLM accuracy for citation generation in lengthy documents?
    you: not recommended
    AI recommended (in order):
    1. LlamaIndex (run-llama/llama_index)
    2. Haystack (deepset-ai/haystack)
    3. FAISS (facebookresearch/faiss)
    4. Annoy (spotify/annoy)
    5. Pinecone
    6. Weaviate (weaviate/weaviate)
    7. ChromaDB (chroma-core/chroma)
    8. Sentence-BERT (UKPLab/sentence-transformers)
    9. OpenAI Embeddings
    10. OpenAI API
    11. Hugging Face Transformers (huggingface/transformers)
    12. Llama 2 (facebookresearch/llama)
    13. Mistral (mistralai/mistral-src)
    14. Anthropic Claude
    15. Python's `re` module
    16. SpaCy (explosion/spaCy)
    17. Zotero (zotero/zotero)
    18. Mendeley APIs

    AI recommended 18 alternatives but never named THUDM/LongCite. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Seeking a method to fine-tune LLMs for precise citation output in long-form question answering.
    you: not recommended
    AI recommended (in order):
    1. OpenAI API
    2. Hugging Face Transformers (huggingface/transformers)
    3. Ludwig (ludwig-ai/ludwig)
    4. Google Cloud Vertex AI
    5. Weights & Biases (W&B) (wandb/wandb)
    6. DeepSpeed (microsoft/DeepSpeed)
    7. FSDP

    AI recommended 7 alternatives but never named THUDM/LongCite. 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 THUDM/LongCite?
    pass
    AI named THUDM/LongCite explicitly

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

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

Subscribe to Pro for deep diagnoses

THUDM/LongCite — 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