Human-like intuitive behavior and reasoning biases emerged in large language models but disappeared in ChatGPT.
Thilo HagendorffSarah FabiMichal KosinskiPublished in: Nat. Comput. Sci. (2023)
Keyphrases
- language model
- language modeling
- n gram
- human behavior
- probabilistic model
- speech recognition
- document retrieval
- retrieval model
- information retrieval
- query expansion
- language models for information retrieval
- statistical language models
- language modelling
- smoothing methods
- vector space model
- document ranking
- context sensitive
- test collection
- relevance model
- translation model
- document length
- query terms
- pseudo relevance feedback
- ad hoc information retrieval
- query specific
- retrieval effectiveness
- pseudo feedback
- language model for information retrieval