Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models.
Carson DenisonMonte MacDiarmidFazl BarezDavid DuvenaudShauna KravecSamuel MarksNicholas SchieferRyan SoklaskiAlex TamkinJared KaplanBuck ShlegerisSamuel R. BowmanEthan PerezEvan HubingerPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- information retrieval
- document retrieval
- query expansion
- speech recognition
- retrieval model
- language modelling
- test collection
- vector space model
- mixture model
- statistical language models
- language model for information retrieval
- pseudo relevance feedback
- query terms
- translation model
- document ranking
- context sensitive
- knn
- multimedia
- passage retrieval
- smoothing methods
- feature selection
- word error rate
- search engine
- ad hoc information retrieval
- language models for information retrieval
- machine learning