Evaluating Large Language Models for Generalization and Robustness via Data Compression.
Yucheng LiYunhao GuoFrank GuerinChenghua LinPublished in: CoRR (2024)
Keyphrases
- data compression
- language model
- language modeling
- document retrieval
- n gram
- probabilistic model
- compression algorithm
- information retrieval
- data reduction
- retrieval model
- speech recognition
- test collection
- language modelling
- compression ratio
- language models for information retrieval
- query terms
- context sensitive
- statistical language models
- query expansion
- ad hoc information retrieval
- huffman coding
- language model for information retrieval
- translation model
- pseudo relevance feedback
- smoothing methods
- document ranking
- vector space model
- image quality
- lossless data compression
- data structure