CRASS: A Novel Data Set and Benchmark to Test Counterfactual Reasoning of Large Language Models.
Jörg FrohbergFrank BinderPublished in: CoRR (2021)
Keyphrases
- recommender systems
- language model
- data sets
- language modeling
- speech recognition
- n gram
- language modelling
- retrieval model
- information retrieval
- document retrieval
- probabilistic model
- statistical language models
- query expansion
- smoothing methods
- test collection
- document ranking
- language model for information retrieval
- ad hoc information retrieval
- passage retrieval
- logical framework
- query terms
- okapi bm
- training set
- relevance model
- causal reasoning
- query specific
- clustering algorithm
- word error rate
- pseudo relevance feedback
- vector space model
- training data
- document length
- bayesian networks
- question answering