CLadder: A Benchmark to Assess Causal Reasoning Capabilities of Language Models.
Zhijing JinYuen ChenFelix LeebLuigi GreseleOjasv KamalZhiheng LyuKevin BlinFernando Gonzalez AdautoMax Kleiman-WeinerMrinmaya SachanBernhard SchölkopfPublished in: NeurIPS (2023)
Keyphrases
- language model
- causal reasoning
- language modeling
- probabilistic model
- n gram
- document retrieval
- speech recognition
- information retrieval
- language modelling
- query expansion
- context sensitive
- retrieval model
- causal models
- statistical language models
- pseudo relevance feedback
- knowledge representation
- test collection
- smoothing methods
- default logic
- language model for information retrieval
- vector space model
- retrieval effectiveness
- directed acyclic graph
- relevance model
- translation model
- graphical models
- data mining
- query terms