RRepoGEO

REPOGEO REPORT · LITE

THUDM/LongWriter

Default branch main · commit 447539b3 · scanned 5/21/2026, 7:13:20 PM

GitHub: 1,859 stars · 185 forks

Scan history for this repo

Score trend below includes all ready runs (older left, newer right; scroll horizontally if needed). The table is collapsed by default—expand for newest-first rows, 10 per page.

Score trend (left → right: older → newer)

2 ready scans. Expand the table below for newest-first rows (10 per page, paginated).

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/LongWriter, 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 an explicit introductory sentence to the README

    Why:

    COPY-PASTE FIX
    Insert the following sentence immediately after the main title: 'This repository presents LongWriter, a novel model and method for efficient ultra-long text generation (10,000+ words) with large language models, offering a distinct approach from general LLM APIs or frameworks.'
  • mediumtopics#2
    Expand repository topics to improve category recall

    Why:

    CURRENT
    fine-tuning, llm, long-context, long-text
    COPY-PASTE FIX
    fine-tuning, llm, long-context, long-text, text-generation, large-language-model, long-form-generation
  • lowhomepage#3
    Add a homepage URL to the repository's About section

    Why:

    COPY-PASTE FIX
    https://arxiv.org/abs/2408.07055

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/LongWriter
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Anthropic Claude
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. Anthropic Claude · recommended 1×
  2. OpenAI GPT-4 · recommended 1×
  3. Google Gemini 1.5 Pro · recommended 1×
  4. langchain-ai/langchain · recommended 1×
  5. run-llama/llama_index · recommended 1×
  • CATEGORY QUERY
    How can I generate extremely long text documents using large language models effectively?
    you: not recommended
    AI recommended (in order):
    1. Anthropic Claude
    2. OpenAI GPT-4
    3. Google Gemini 1.5 Pro
    4. LangChain (langchain-ai/langchain)
    5. LlamaIndex (run-llama/llama_index)
    6. OpenAI's fine-tuning API
    7. Llama 2
    8. Mistral
    9. Guidance (microsoft/guidance)

    AI recommended 9 alternatives but never named THUDM/LongWriter. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Looking for methods to fine-tune LLMs for ultra-long text generation without synthetic data.
    you: not recommended
    AI recommended (in order):
    1. Hugging Face Transformers
    2. PyTorch
    3. Hugging Face PEFT Library
    4. YaRN (Yet another RoPE extensioN)
    5. LongT5
    6. Hyena Hierarchy
    7. Mamba
    8. Hugging Face Trainer
    9. Microsoft DeepSpeed
    10. PyTorch FSDP (Fully Sharded Data Parallel)

    AI recommended 10 alternatives but never named THUDM/LongWriter. 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/LongWriter?
    pass
    AI named THUDM/LongWriter 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/LongWriter in production, what risks or prerequisites should they evaluate first?
    pass
    AI named THUDM/LongWriter 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/LongWriter solve, and who is the primary audience?
    pass
    AI named THUDM/LongWriter 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/LongWriter. 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/LongWriter.svg)](https://repogeo.com/en/r/THUDM/LongWriter)
HTML
<a href="https://repogeo.com/en/r/THUDM/LongWriter"><img src="https://repogeo.com/badge/THUDM/LongWriter.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

THUDM/LongWriter — 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