DyKnow-RAG uses Group Relative Policy Optimization with dual-group rollouts and posterior-driven advantage scaling to optimize context utilization in RAG for e-commerce relevance, showing offline gains and production lifts when deployed at Taobao.
Astute rag: Overcoming imperfect retrieval augmentation and knowledge conflicts for large language models
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
PMSR progressively constructs structured reasoning trajectories with dual-scope queries and compositional reasoning to improve knowledge acquisition and answer accuracy in knowledge-intensive VQA.
A conformal prediction filter for retrieval chunks plus an attention-based factuality classifier can raise RAG answer quality by up to 6% and detect inconsistent generations up to 77% of the time.
Interacting Gaussian mixture models with RAG-style updates are shown to mimic aspects of interacting LLMs and are used to prove lower bounds on polarization probability in the resulting Markov chain.
citing papers explorer
-
Learning to Trust: Dynamic Utilization of Retrieval-Augmented Generation for E-commerce Search Relevance
DyKnow-RAG uses Group Relative Policy Optimization with dual-group rollouts and posterior-driven advantage scaling to optimize context utilization in RAG for e-commerce relevance, showing offline gains and production lifts when deployed at Taobao.
-
Progressive Multimodal Search and Reasoning for Knowledge-Intensive Visual Question Answering
PMSR progressively constructs structured reasoning trajectories with dual-scope queries and compositional reasoning to improve knowledge acquisition and answer accuracy in knowledge-intensive VQA.
-
Towards Dependable Retrieval-Augmented Generation Using Factual Confidence Prediction
A conformal prediction filter for retrieval chunks plus an attention-based factuality classifier can raise RAG answer quality by up to 6% and detect inconsistent generations up to 77% of the time.
-
Gaussian mixture models as a proxy for interacting language models
Interacting Gaussian mixture models with RAG-style updates are shown to mimic aspects of interacting LLMs and are used to prove lower bounds on polarization probability in the resulting Markov chain.
- Does RAG Know When Retrieval Is Wrong? Diagnosing Context Compliance under Knowledge Conflict