Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Models.
Xinran ZhaoHongming ZhangXiaoman PanWenlin YaoDong YuTongshuang WuJianshu ChenPublished in: ACL (Findings) (2024)
Keyphrases
- language model
- language modeling
- n gram
- speech recognition
- document retrieval
- probabilistic model
- information retrieval
- retrieval model
- query expansion
- test collection
- context sensitive
- ad hoc information retrieval
- smoothing methods
- language modelling
- statistical language models
- document ranking
- document length
- statistical language modeling
- pseudo relevance feedback
- language model for information retrieval
- relevance model
- vector space model
- retrieval effectiveness