When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards.
Norah AlzahraniHisham Abdullah AlyahyaYazeed AlnumaySultan AlrashedShaykhah AlsubaieYousef AlmushayqihFaisal MirzaNouf AlotaibiNora Al-TwaireshAreeb AlowisheqM. Saiful BariHaidar KhanPublished in: ACL (1) (2024)
Keyphrases
- language model
- language modeling
- information retrieval
- retrieval model
- n gram
- document retrieval
- probabilistic model
- query expansion
- speech recognition
- context sensitive
- test collection
- language model for information retrieval
- ad hoc information retrieval
- mixture model
- vector space model
- query terms
- statistical language models
- language modelling
- translation model
- pseudo relevance feedback
- document ranking
- relevance model
- document length
- retrieval effectiveness
- statistical machine translation
- query specific
- word error rate
- pseudo feedback
- term weighting
- dirichlet prior