REPOGEO REPORT · LITE
google-deepmind/long-form-factuality
Default branch main · commit 9d27158d · scanned 6/3/2026, 3:22:54 PM
GitHub: 687 stars · 86 forks
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 google-deepmind/long-form-factuality, 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.
- highreadme#1Reposition README's opening to highlight problem and solution
Why:
CURRENT# Long-Form Factuality in Large Language Models This is the official code release accompanying our paper "Long-form factuality in large language models".
COPY-PASTE FIX# Long-Form Factuality in Large Language Models This repository provides the official code for benchmarking and automatically evaluating the factual accuracy of long-form text generated by large language models. It introduces LongFact, a novel dataset of fact-seeking prompts, and SAFE, an automatic evaluation framework specifically designed for multi-paragraph LLM responses.
- mediumlicense#2Clarify the project's license(s) in the README
Why:
COPY-PASTE FIXAdd a section to the README, perhaps under "About" or "Contributing", stating: "This project is licensed under [INSERT SPECIFIC LICENSE(S) HERE, e.g., Apache 2.0 for code and CC BY 4.0 for data]. Please refer to the LICENSE file for full details."
- lowabout#3Refine the repository's "About" description
Why:
CURRENTBenchmarking long-form factuality in large language models. Original code for our paper "Long-form factuality in large language models".
COPY-PASTE FIXOfficial code for benchmarking and automatically evaluating the factual accuracy of long-form text generated by large language models. Includes the LongFact dataset and SAFE evaluation framework.
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.
- FactScore · recommended 2×
- LlamaIndex · recommended 1×
- LangChain · recommended 1×
- Haystack · recommended 1×
- SelfCheckGPT · recommended 1×
- CATEGORY QUERYHow to automatically evaluate the factual accuracy of long-form text generated by large language models?you: not recommendedAI recommended (in order):
- LlamaIndex
- LangChain
- Haystack
- FactScore
- SelfCheckGPT
- OpenAI GPT-4 / GPT-4o
- Anthropic Claude 3 Opus
- spaCy
- Wikidata Query Service
AI recommended 9 alternatives but never named google-deepmind/long-form-factuality. This is the gap to close.
Show full AI answer
- CATEGORY QUERYWhat are effective metrics and datasets for assessing factuality in lengthy AI-generated content?you: not recommendedAI recommended (in order):
- FactScore
- ROUGE scores
- BERTScore
- MoverScore
- FEVER
- ELI5
- WikiFact
- TruthfulQA
- LongFact
- NarrativeQA
AI recommended 10 alternatives but never named google-deepmind/long-form-factuality. This is the gap to close.
Show full AI answer
Objective checks
Rule-based audits of metadata signals AI engines weight most.
- Metadata completenesspass
- README presencepass
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 google-deepmind/long-form-factuality?passAI did not name google-deepmind/long-form-factuality — 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 google-deepmind/long-form-factuality in production, what risks or prerequisites should they evaluate first?passAI named google-deepmind/long-form-factuality 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 google-deepmind/long-form-factuality solve, and who is the primary audience?passAI did not name google-deepmind/long-form-factuality — 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?
Embed your GEO score
Drop this badge into the README of google-deepmind/long-form-factuality. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.
Live preview[](https://repogeo.com/en/r/google-deepmind/long-form-factuality)<a href="https://repogeo.com/en/r/google-deepmind/long-form-factuality"><img src="https://repogeo.com/badge/google-deepmind/long-form-factuality.svg" alt="RepoGEO" /></a>Subscribe to Pro for deep diagnoses
google-deepmind/long-form-factuality — 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