Induced Natural Language Rationales and Interleaved Markup Tokens Enable Extrapolation in Large Language Models.
Mirelle BuenoCarlos GemmelJeffrey DaltonRoberto de Alencar LotufoRodrigo NogueiraPublished in: CoRR (2022)
Keyphrases
- language model
- natural language
- language modeling
- n gram
- information retrieval
- document retrieval
- query expansion
- probabilistic model
- retrieval model
- context sensitive
- language modelling
- speech recognition
- ad hoc information retrieval
- test collection
- statistical language models
- pseudo relevance feedback
- information extraction
- smoothing methods
- document ranking
- question answering
- machine learning
- language processing
- relevance model
- word error rate
- feature selection
- collaborative filtering
- query terms
- natural language processing
- okapi bm
- bayesian networks