Cache & Distil: Optimising API Calls to Large Language Models.
Guillem RamírezMatthias LindemannAlexandra BirchIvan TitovPublished in: ACL (Findings) (2024)
Keyphrases
- language model
- malware detection
- language modeling
- api calls
- static analysis
- probabilistic model
- document retrieval
- n gram
- information retrieval
- retrieval model
- language modelling
- speech recognition
- test collection
- query processing
- query expansion
- pseudo relevance feedback
- statistical language models
- database
- data access
- cd rom
- third party
- source code
- relevance model
- application programming interface
- spoken term detection
- relational databases
- smoothing methods
- query language
- document ranking
- knowledge discovery
- unsupervised learning