www.librai.tech Open in urlscan Pro
142.250.186.83  Public Scan

Form analysis
0 forms found in the DOM

Text Content

Auf dieser Website suchen





Zum Hauptinhalt springen

Zur Navigation springen

 * LibrAI
 * Products
 * Blog
 * Team

 
 * LibrAI
   
 * Products
   
 * Blog
   
 * Team
   
 * Mehr
   
    * LibrAI
    * Products
    * Blog
    * Team






BUILD AI TO 


SHAPE TOMORROW'S SAFEST AGI 




OUR MISSION



AT LIBRAI, WE LEVERAGE AI TO DELIVER COMPREHENSIVE AND MULTIDIMENSIONAL
EVALUATION AND IMPROVEMENT SOLUTIONS FOR AI SAFETY.


PRODUCTS




EVALUATION FRAMEWORK


FACT-CHECKING ASSISTANT


LIFELONG SAFETY MANAGEMENT


HIGHLIGHTS

Factcheck-GPT: End-to-End Fine-Grained Document-Level Fact-Checking and
Correction of LLM Output
M4: Multi-generator, Multi-domain, and Multi-lingual Black-Box Machine-Generated
Text Detection
Everybody needs good neighbours: An unsupervised locality-based method for bias
mitigation
Balancing out Bias: Achieving Fairness Through Balanced Training
FairLib: A unified framework for assessing and improving fairness
Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs
CMMLU: Measuring massive multitask language understanding in Chinese


CO-FOUNDERS

Xudong Han （CEO）

Haonan Li (CTO)

Yuxia Wang (COO)

Timothy Baldwin (Advisor)



© 2024 LibrAI. All rights reserved.

Email: team@librai.tech

Google Sites
Missbrauch melden
Diese Website verwendet Cookies von Google, um ihre Dienste bereitzustellen und
Zugriffe zu analysieren. Informationen darüber, wie Sie die Website verwenden,
werden an Google weitergegeben. Durch die Nutzung dieser Website erklären Sie
sich damit einverstanden, dass auf der Website Cookies verwendet werden.
Weitere Informationen
Ok