CALM-Bench: A Multi-task Benchmark for Evaluating Causality-Aware Language Models.
Dhairya DalalPaul BuitelaarMihael ArcanPublished in: EACL (Findings) (2023)
Keyphrases
- language model
- multi task
- multi task learning
- language modeling
- learning tasks
- n gram
- probabilistic model
- multiple tasks
- multi class
- language modelling
- document retrieval
- gaussian processes
- transfer learning
- information retrieval
- sparse learning
- smoothing methods
- feature selection
- test collection
- learning problems
- query expansion
- statistical language models
- machine learning algorithms
- retrieval model
- language models for information retrieval
- natural language processing
- classification accuracy
- relevance model
- pairwise
- decision trees
- machine learning