PARIKSHA : A Large-Scale Investigation of Human-LLM Evaluator Agreement on Multilingual and Multi-Cultural Data.
Ishaan WattsVarun GummaAditya YadavalliVivek SeshadriManohar SwaminathanSunayana SitaramPublished in: CoRR (2024)
Keyphrases
- data sets
- data sources
- data collection
- data analysis
- raw data
- database
- synthetic data
- training data
- data structure
- data processing
- human experts
- machine learning
- databases
- data objects
- search engine
- data distribution
- statistical analysis
- input data
- co occurrence
- end users
- prior knowledge
- data streams
- video sequences
- high quality