Detecting and Understanding Vulnerabilities in Language Models via Mechanistic Interpretability.
Jorge García-CarrascoAlejandro MatéJuan TrujilloPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- speech recognition
- probabilistic model
- language modelling
- document retrieval
- information retrieval
- query expansion
- retrieval model
- smoothing methods
- test collection
- statistical language models
- ad hoc information retrieval
- context sensitive
- translation model
- query terms
- prediction accuracy
- language model for information retrieval
- document ranking
- language models for information retrieval
- relevance model