Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling.
Stella BidermanHailey SchoelkopfQuentin AnthonyHerbie BradleyKyle O'BrienEric HallahanMohammad Aflah KhanShivanshu PurohitUSVSN Sai PrashanthEdward RaffAviya SkowronLintang SutawikaOskar van der WalPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- n gram
- speech recognition
- probabilistic model
- language modelling
- document retrieval
- test collection
- statistical language models
- context sensitive
- query expansion
- information retrieval
- retrieval model
- training set
- pseudo relevance feedback
- relevance model
- language model for information retrieval
- smoothing methods
- ad hoc information retrieval
- language models for information retrieval
- retrieval effectiveness
- vector space model
- translation model
- document length
- machine learning
- information retrieval systems