Supporting Human Raters with the Detection of Harmful Content using Large Language Models.
Kurt ThomasPatrick Gage KelleyDavid TaoSarah MeiklejohnOwen VallisShunwen TanBlaz BratanicFelipe Tiengo FerreiraVijay Kumar ErantiElie BurszteinPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- probabilistic model
- information retrieval
- n gram
- document retrieval
- speech recognition
- retrieval model
- language modelling
- context sensitive
- statistical language models
- test collection
- query expansion
- ad hoc information retrieval
- relevance model
- smoothing methods
- word clouds
- language model for information retrieval
- query terms
- translation model
- semantic information
- vector space model
- machine learning
- pseudo relevance feedback
- document ranking
- web documents