CG-FedLLM: How to Compress Gradients in Federated Fune-tuning for Large Language Models.
Huiwen WuXiaohan LiDeyi ZhangXiaogang XuJiafei WuPuning ZhaoZhe LiuPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- document retrieval
- speech recognition
- language modelling
- probabilistic model
- information retrieval
- query expansion
- retrieval model
- context sensitive
- test collection
- ad hoc information retrieval
- statistical language models
- language model for information retrieval
- language models for information retrieval
- query terms
- relevance model
- translation model
- document ranking
- federated search
- query specific
- smoothing methods
- word error rate
- vector space model
- pseudo relevance feedback
- term dependencies
- machine learning
- bayesian networks
- retrieval effectiveness
- error rate