Likelihood-based Mitigation of Evaluation Bias in Large Language Models.
Masanari OhiMasahiro KanekoRyuto KoikeMengsay LoemNaoaki OkazakiPublished in: ACL (Findings) (2024)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- information retrieval
- speech recognition
- language modelling
- test collection
- document retrieval
- retrieval model
- query expansion
- vector space model
- statistical language models
- context sensitive
- language models for information retrieval
- relevance model
- translation model
- word error rate
- okapi bm
- text retrieval
- pseudo relevance feedback
- document ranking
- query specific
- smoothing methods
- error rate
- document length
- text classification
- spoken term detection
- language model for information retrieval