Structured, flexible, and robust: benchmarking and improving large language models towards more human-like behavior in out-of-distribution reasoning tasks.
Katherine M. CollinsCatherine WongJiahai FengMegan WeiJoshua B. TenenbaumPublished in: CoRR (2022)
Keyphrases
- language model
- reasoning tasks
- language modeling
- n gram
- description logics
- probabilistic model
- speech recognition
- automated reasoning
- document retrieval
- information retrieval
- statistical language models
- logic programming
- retrieval model
- temporal reasoning
- language modelling
- answer set programming
- query expansion
- test collection
- situation calculus
- smoothing methods
- language models for information retrieval
- query terms
- context sensitive
- vector space model
- knowledge representation
- probability distribution
- high level
- qualitative and quantitative
- retrieval effectiveness
- probabilistic reasoning
- vector space
- okapi bm
- data mining