Self-Explore to Avoid the Pit: Improving the Reasoning Capabilities of Language Models with Fine-grained Rewards.
Hyeonbin HwangDoyoung KimSeungone KimSeonghyeon YeMinjoon SeoPublished in: CoRR (2024)
Keyphrases
- fine grained
- language model
- coarse grained
- language modeling
- document retrieval
- n gram
- speech recognition
- probabilistic model
- context sensitive
- access control
- retrieval model
- information retrieval
- language modelling
- statistical language models
- test collection
- query expansion
- smoothing methods
- document ranking
- vector space model
- pseudo relevance feedback
- language models for information retrieval
- knowledge base
- translation model
- query terms
- high level
- improving web search
- relevance model
- data lineage