metabench - A Sparse Benchmark to Measure General Ability in Large Language Models.
Alex KipnisKonstantinos VoudourisLuca M. Schulze BuschoffEric SchulzPublished in: CoRR (2024)
Keyphrases
- co occurrence
- language model
- language modeling
- query terms
- probabilistic model
- query expansion
- speech recognition
- document retrieval
- language modelling
- test collection
- information retrieval
- n gram
- statistical language models
- retrieval model
- similarity measure
- document length
- language model for information retrieval
- document ranking
- smoothing methods
- high dimensional
- ad hoc information retrieval
- relevance model
- word error rate