Don't Believe Everything You Read: Enhancing Summarization Interpretability through Automatic Identification of Hallucinations in Large Language Models.
Priyesh VakhariaDevavrat JoshiMeenal ChavanDhananjay SonawaneBhrigu GargParsa MazaheriIan LanePublished in: CoRR (2023)
Keyphrases
- automatic identification
- language model
- language modeling
- n gram
- document retrieval
- probabilistic model
- query expansion
- statistical language models
- information retrieval
- language modelling
- test collection
- retrieval model
- pseudo relevance feedback
- speech recognition
- query terms
- vector space model
- text summarization
- context sensitive
- smoothing methods
- document ranking
- language models for information retrieval
- translation model
- multi document summarization
- bayesian networks
- term dependencies
- text classification
- ad hoc information retrieval
- image processing