CRiskEval: A Chinese Multi-Level Risk Evaluation Benchmark Dataset for Large Language Models.
Ling ShiDeyi XiongPublished in: CoRR (2024)
Keyphrases
- language model
- benchmark datasets
- risk evaluation
- risk management
- language modeling
- n gram
- probabilistic model
- word segmentation
- information retrieval
- document retrieval
- speech recognition
- retrieval model
- technological innovation
- query expansion
- language modelling
- statistical language models
- test collection
- context sensitive
- smoothing methods
- query terms
- text summarization
- pseudo relevance feedback
- ad hoc information retrieval
- vector space model
- spoken term detection
- data mining
- language model for information retrieval
- okapi bm
- expert systems
- key factors
- relevance model
- knowledge management