TabLLM: Few-shot Classification of Tabular Data with Large Language Models.
Stefan HegselmannAlejandro BuendiaHunter LangMonica AgrawalXiaoyi JiangDavid A. SontagPublished in: AISTATS (2023)
Keyphrases
- language model
- tabular data
- language modeling
- probabilistic model
- n gram
- document retrieval
- speech recognition
- image classification
- document ranking
- retrieval model
- query expansion
- test collection
- statistical language models
- language modelling
- classification accuracy
- information retrieval
- feature vectors
- feature selection
- decision trees
- machine learning
- web search
- smoothing methods