UniTSyn: A Large-Scale Dataset Capable of Enhancing the Prowess of Large Language Models for Program Testing.
Yifeng HeJiabo HuangYuyang RongYiwen GuoEthan WangHao ChenPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- document retrieval
- test cases
- n gram
- probabilistic model
- query expansion
- information retrieval
- statistical language models
- smoothing methods
- language modelling
- test collection
- retrieval model
- speech recognition
- context sensitive
- language models for information retrieval
- pseudo relevance feedback
- query specific
- cross lingual
- language model for information retrieval
- okapi bm
- document ranking
- passage retrieval