Can Prompt Probe Pretrained Language Models? Understanding the Invisible Risks from a Causal View.
Boxi CaoHongyu LinXianpei HanFangchao LiuLe SunPublished in: ACL (1) (2022)
Keyphrases
- language model
- language modeling
- n gram
- speech recognition
- information retrieval
- document retrieval
- probabilistic model
- query expansion
- statistical language models
- retrieval model
- language modelling
- context sensitive
- test collection
- smoothing methods
- query terms
- language models for information retrieval
- pseudo relevance feedback
- ad hoc information retrieval
- bayesian networks
- document ranking
- vector space model
- passage retrieval
- translation model
- word error rate
- document collections