ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models.
Yuxiang ZhangJing ChenJunjie WangYaxin LiuCheng YangChufan ShiXinyu ZhuZihao LinHanwen WanYujiu YangTetsuya SakaiTian FengHayato YamanaPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- document retrieval
- speech recognition
- language modelling
- probabilistic model
- language models for information retrieval
- statistical language models
- information retrieval
- retrieval model
- test collection
- query expansion
- document ranking
- language model for information retrieval
- pseudo relevance feedback
- vector space model
- smoothing methods
- context sensitive
- ad hoc information retrieval
- query terms
- cross lingual
- pseudo feedback
- spoken term detection
- feature selection