Q-Probe: A Lightweight Approach to Reward Maximization for Language Models.
Kenneth LiSamy JelassiHugh ZhangSham M. KakadeMartin WattenbergDavid BrandfonbrenerPublished in: CoRR (2024)
Keyphrases
- lightweight
- language model
- language modeling
- n gram
- speech recognition
- information retrieval
- probabilistic model
- document retrieval
- retrieval model
- language modelling
- query expansion
- test collection
- query terms
- ad hoc information retrieval
- smoothing methods
- statistical language models
- context sensitive
- pseudo relevance feedback
- communication infrastructure
- language models for information retrieval
- document length
- okapi bm
- spoken term detection
- document ranking
- vector space model
- retrieval effectiveness
- wireless sensor networks