The Devil is in the Tails: How Long-Tailed Code Distributions Impact Large Language Models.
Xin ZhouKisub KimBowen XuJiakun LiuDongGyun HanDavid LoPublished in: ASE (2023)
Keyphrases
- language model
- heavy tails
- heavy tailed
- language modeling
- n gram
- language modelling
- gaussian distribution
- probabilistic model
- speech recognition
- document retrieval
- retrieval model
- information retrieval
- query expansion
- test collection
- context sensitive
- mixture model
- probability distribution
- smoothing methods
- document ranking
- ad hoc information retrieval
- pseudo relevance feedback
- translation model
- statistical language models
- document length
- language model for information retrieval
- generalized gaussian
- query terms
- query specific
- prior distribution
- vector space model
- web pages