O3D: Offline Data-driven Discovery and Distillation for Sequential Decision-Making with Large Language Models.
Yuchen XiaoYanchao SunMengda XuUdari MadhushaniJared VannDeepeka GargSumitra GaneshPublished in: CoRR (2023)
Keyphrases
- language model
- sequential decision making
- data driven
- language modeling
- decision problems
- reinforcement learning
- influence diagrams
- interactive dynamic influence diagrams
- n gram
- probabilistic model
- speech recognition
- document retrieval
- language modelling
- information retrieval
- temporal difference
- retrieval model
- test collection
- context sensitive
- language models for information retrieval
- vector space model
- smoothing methods
- query expansion
- statistical language models
- relevance model
- expected utility
- translation model
- special case
- pseudo relevance feedback
- machine learning
- sensitivity analysis
- tf idf