ASSERT: Automated Safety Scenario Red Teaming for Evaluating the Robustness of Large Language Models.
Alex MeiSharon LevyWilliam Yang WangPublished in: EMNLP (Findings) (2023)
Keyphrases
- language model
- language modeling
- context sensitive
- speech recognition
- n gram
- document retrieval
- statistical language models
- information retrieval
- query expansion
- probabilistic model
- retrieval model
- language modelling
- test collection
- ad hoc information retrieval
- vector space model
- document ranking
- translation model
- language model for information retrieval
- language models for information retrieval
- pseudo relevance feedback
- document length
- query terms
- term dependencies
- smoothing methods
- cross lingual
- collaborative filtering
- okapi bm
- naive bayes
- retrieval effectiveness