TabLLM: Few-shot Classification of Tabular Data with Large Language Models.
Stefan HegselmannAlejandro BuendiaHunter LangMonica AgrawalXiaoyi JiangDavid A. SontagPublished in: CoRR (2022)
Keyphrases
- language model
- tabular data
- language modeling
- n gram
- classification accuracy
- information retrieval
- speech recognition
- probabilistic model
- document retrieval
- statistical language models
- retrieval model
- text classification
- language modelling
- test collection
- feature selection
- query expansion
- feature space
- smoothing methods
- machine learning
- model selection
- feature vectors
- visual features
- document ranking
- language models for information retrieval