RRepoGEO

REPOGEO REPORT · LITE

thu-coai/CDial-GPT

Default branch master · commit 81064865 · scanned 6/23/2026, 2:13:38 PM

GitHub: 1,952 stars · 260 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 thu-coai/CDial-GPT, 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 concise English summary to the README

    Why:

    COPY-PASTE FIX
    Add this text at the very top of the README, before the Chinese title:

```
This repository provides CDial-GPT, a suite of pre-trained GPT models specifically designed for Chinese dialogue generation, alongside LCCC (Large-scale Cleaned Chinese Conversation), a high-quality, large-scale dataset for training Chinese conversational AI.
```
  • mediumhomepage#2
    Add a homepage URL to the repository metadata

    Why:

    COPY-PASTE FIX
    https://aclanthology.org/2020.nlpcc-1.10/
  • mediumreadme#3
    Reorganize README to clearly separate CDial-GPT's core offerings from related projects

    Why:

    COPY-PASTE FIX
    Move the 'News' section content that is not directly about CDial-GPT or LCCC (e.g., MMChat, SentiLARE, cleaning framework, book) into a new, dedicated section titled 'Related Projects' or 'Other Projects from Our Lab' at the end of the README. Keep only CDial-GPT/LCCC specific news in the main 'News' section.

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 thu-coai/CDial-GPT
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
LCCC
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. LCCC · recommended 1×
  2. Baidu Wenxin · recommended 1×
  3. ERNIE · recommended 1×
  4. SMP-MCC · recommended 1×
  5. Douban Conversation Corpus · recommended 1×
  • CATEGORY QUERY
    Where can I find a large-scale dataset for training Chinese conversational AI models?
    you: not recommended
    AI recommended (in order):
    1. LCCC
    2. Baidu Wenxin
    3. ERNIE
    4. SMP-MCC
    5. Douban Conversation Corpus
    6. Tsinghua-THUCNews

    AI recommended 6 alternatives but never named thu-coai/CDial-GPT. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What are the best pre-trained GPT models for generating Chinese dialogue responses?
    you: not recommended
    AI recommended (in order):
    1. ERNIE 3.0 Titan
    2. CPM-2
    3. Pangu-α
    4. ChatGLM
    5. BELLE
    6. Qwen
    7. OpenAI GPT-3.5
    8. GPT-4

    AI recommended 8 alternatives but never named thu-coai/CDial-GPT. 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 thu-coai/CDial-GPT?
    pass
    AI named thu-coai/CDial-GPT explicitly

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

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

Subscribe to Pro for deep diagnoses

thu-coai/CDial-GPT — 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