A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners.
Bowen JiangYangxinyu XieZhuoqun HaoXiaomeng WangTanwi MallickWeijie J. SuCamillo J. TaylorDan RothPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- document retrieval
- speech recognition
- probabilistic model
- retrieval model
- n gram
- test collection
- information retrieval
- language modelling
- query expansion
- ad hoc information retrieval
- context sensitive
- statistical language models
- query terms
- vector space model
- word error rate
- document length
- language models for information retrieval
- smoothing methods
- query specific
- relevance model
- pseudo relevance feedback
- relevant documents
- document ranking
- document collections
- bayesian networks