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: CoRR (2023)
Keyphrases
- language model
- causal reasoning
- language modeling
- document retrieval
- n gram
- causal models
- retrieval model
- speech recognition
- probabilistic model
- language modelling
- information retrieval
- query expansion
- test collection
- statistical language models
- query terms
- ad hoc information retrieval
- smoothing methods
- okapi bm
- context sensitive
- vector space model
- pseudo relevance feedback
- language models for information retrieval
- directed acyclic graph
- retrieval effectiveness
- knowledge representation
- translation model
- relevance model
- web search
- default logic
- document length
- artificial intelligence