Is Crowdsourcing Breaking Your Bank? Cost-Effective Fine-Tuning of Pre-trained Language Models with Proximal Policy Optimization.
Shuo YangGjergji KasneciPublished in: CoRR (2024)
Keyphrases
- cost effective
- fine tuning
- language model
- pre trained
- language modeling
- low cost
- n gram
- probabilistic model
- document retrieval
- speech recognition
- retrieval model
- query expansion
- information retrieval
- language modelling
- statistical language models
- cost effectiveness
- smoothing methods
- test collection
- fine tuned
- neural network
- training data
- real time
- relevance model
- training examples
- machine learning
- language models for information retrieval
- supervised learning
- small number
- computer vision
- spoken term detection