Softmax Probabilities (Mostly) Predict Large Language Model Correctness on Multiple-Choice Q&A.
Benjamin PlautKhanh NguyenTu TrinhPublished in: CoRR (2024)
Keyphrases
- language model
- multiple choice
- language modeling
- open ended
- probabilistic model
- n gram
- speech recognition
- information retrieval
- document retrieval
- query expansion
- retrieval model
- test collection
- smoothing methods
- language modelling
- statistical language models
- mixture model
- ad hoc information retrieval
- language model for information retrieval
- query terms
- exam questions
- probability distribution
- query specific
- translation model
- relevance feedback
- word clouds
- machine learning