RRepoGEO

REPOGEO REPORT · LITE

EdinburghNLP/awesome-hallucination-detection

Default branch main · commit a633c98f · scanned 6/19/2026, 2:07:52 PM

GitHub: 1,105 stars · 90 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
28 /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
2 / 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 EdinburghNLP/awesome-hallucination-detection, 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
    Add this sentence immediately after the main title: "This repository serves as a curated and comprehensive 'awesome list' of research papers, datasets, and resources specifically focused on hallucination detection in Large Language Models (LLMs)."
  • mediumtopics#2
    Add topics to clarify the repo's nature as a research collection

    Why:

    CURRENT
    hallucinations, llms, nlp
    COPY-PASTE FIX
    hallucinations, llms, nlp, awesome-list, research-papers, ai-safety, factual-consistency
  • lowhomepage#3
    Add a homepage URL to the repository metadata

    Why:

    COPY-PASTE FIX
    https://github.com/EdinburghNLP/awesome-hallucination-detection

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 EdinburghNLP/awesome-hallucination-detection
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Wikidata
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. Wikidata · recommended 2×
  2. OpenAI API · recommended 2×
  3. Google Search · recommended 1×
  4. Bing Search · recommended 1×
  5. Wolfram Alpha · recommended 1×
  • CATEGORY QUERY
    How to identify and mitigate factual inaccuracies generated by large language models?
    you: not recommended
    AI recommended (in order):
    1. Google Search
    2. Bing Search
    3. Wolfram Alpha
    4. Wikipedia API
    5. DBpedia
    6. Wikidata
    7. LangChain
    8. LlamaIndex
    9. Haystack
    10. Label Studio
    11. Prodigy
    12. GPT-4
    13. Claude 3 Opus
    14. Llama 2
    15. Mistral
    16. ChatGPT

    AI recommended 16 alternatives but never named EdinburghNLP/awesome-hallucination-detection. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What are current research methods for improving factual consistency in generative AI models?
    you: not recommended
    AI recommended (in order):
    1. LangChain (langchain-ai/langchain)
    2. LlamaIndex (run-llama/llama_index)
    3. Haystack (deepset-ai/haystack)
    4. FAISS (facebookresearch/faiss)
    5. Weaviate (weaviate/weaviate)
    6. Pinecone
    7. Milvus (milvus-io/milvus)
    8. Chroma (chroma-core/chroma)
    9. Google's Search Generative Experience (SGE)
    10. ChatGPT's Browsing/Web Pilot Feature
    11. Google Search API
    12. SerpApi
    13. Hugging Face Transformers (huggingface/transformers)
    14. OpenAI API
    15. PyTorch (pytorch/pytorch)
    16. TensorFlow (tensorflow/tensorflow)
    17. TRL (Transformer Reinforcement Learning) (huggingface/trl)
    18. DeepSpeed-Chat (microsoft/DeepSpeed-Chat)
    19. OpenAI's InstructGPT/ChatGPT
    20. OpenAI API
    21. Anthropic Claude
    22. Google Gemini API
    23. Llama 2 (facebookresearch/llama)
    24. Neo4j (neo4j/neo4j)
    25. Grakn (now Vaticle's TypeDB) (vaticle/typedb)
    26. Wikidata
    27. Datalog/Prolog-based systems

    AI recommended 27 alternatives but never named EdinburghNLP/awesome-hallucination-detection. 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 EdinburghNLP/awesome-hallucination-detection?
    pass
    AI did not name EdinburghNLP/awesome-hallucination-detection — likely talking about a different project

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

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

Subscribe to Pro for deep diagnoses

EdinburghNLP/awesome-hallucination-detection — 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