RRepoGEO

REPOGEO REPORT · LITE

thunlp/UltraChat

Default branch main · commit 1f613e1b · scanned 5/25/2026, 2:33:39 AM

GitHub: 2,846 stars · 138 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 thunlp/UltraChat, 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
    Clarify the primary purpose for LLM instruction tuning in the README's opening

    Why:

    CURRENT
    The current H1 is "Large-scale, Informative, and Diverse Multi-round Dialogue Data, and Models".
    COPY-PASTE FIX
    Add the sentence "This repository provides UltraChat, a high-quality dataset and powerful UltraLM models specifically designed for instruction tuning and fine-tuning large language models for sophisticated multi-turn conversational AI." immediately after the H1.
  • mediumtopics#2
    Expand repository topics to include specific LLM training methods and model types

    Why:

    CURRENT
    chatbot, chatgpt, deep-learning, large-language-models
    COPY-PASTE FIX
    chatbot, chatgpt, deep-learning, large-language-models, instruction-tuning, fine-tuning, llm-models, conversational-ai, dialogue-dataset
  • lowhomepage#3
    Add the paper URL as the repository homepage

    Why:

    COPY-PASTE FIX
    https://arxiv.org/abs/2305.14233

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 thunlp/UltraChat
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
MultiWOZ
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. MultiWOZ · recommended 1×
  2. DailyDialog · recommended 1×
  3. Persona-Chat · recommended 1×
  4. Wizard of Wikipedia · recommended 1×
  5. Ubuntu Dialogue Corpus · recommended 1×
  • CATEGORY QUERY
    Need a large, diverse dataset for fine-tuning a multi-turn conversational AI model.
    you: not recommended
    AI recommended (in order):
    1. MultiWOZ
    2. DailyDialog
    3. Persona-Chat
    4. Wizard of Wikipedia
    5. Ubuntu Dialogue Corpus
    6. ConvAI2

    AI recommended 6 alternatives but never named thunlp/UltraChat. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What are the best open-source large language models for building sophisticated chatbots?
    you: not recommended
    AI recommended (in order):
    1. Llama 3
    2. Mistral 7B Instruct
    3. Mixtral 8x7B Instruct
    4. Gemma
    5. Falcon
    6. Zephyr
    7. OpenHermes 2.5
    8. Vicuna

    AI recommended 8 alternatives but never named thunlp/UltraChat. 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 thunlp/UltraChat?
    pass
    AI named thunlp/UltraChat explicitly

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

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

Subscribe to Pro for deep diagnoses

thunlp/UltraChat — 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