Enhancing the Capability and Robustness of Large Language Models through Reinforcement Learning-Driven Query Refinement.
Zisu HuangXiaohua WangFeiran ZhangZhibo XuCenyuan ZhangXiaoqing ZhengXuanjing HuangPublished in: CoRR (2024)
Keyphrases
- language model
- query refinement
- reinforcement learning
- information retrieval
- language modeling
- probabilistic model
- n gram
- document retrieval
- web search
- relevance feedback
- query formulation
- retrieval model
- search engine
- test collection
- smoothing methods
- query expansion
- pseudo relevance feedback
- multimedia retrieval
- machine learning
- similarity search
- query terms
- vector space model
- relevant documents
- language models for information retrieval
- active learning
- decision trees
- learning algorithm