Subtle Biases Need Subtler Measures: Dual Metrics for Evaluating Representative and Affinity Bias in Large Language Models.
Abhishek KumarSarfaroz YunusovAli EmamiPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- document retrieval
- n gram
- probabilistic model
- evaluation metrics
- statistical language models
- language modelling
- information retrieval
- speech recognition
- test collection
- evaluation measures
- affinity measure
- vector space model
- retrieval model
- query expansion
- translation model
- document ranking
- ad hoc information retrieval
- context sensitive
- text retrieval
- query terms
- machine learning
- word error rate
- pseudo relevance feedback
- smoothing methods
- machine translation
- language models for information retrieval
- document length
- query specific
- relevance model
- learning to rank