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