We have 2 of 38 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Incentivizing Retrieval-Augmented Generation via Inner Adaptive Context Selection
InnerRAG is a novel paradigm that empowers LLMs to autonomously select relevant context during generation by endowing the model to accurately identify the documents that are most helpful for generation from long contexts, leading to substantial improvements in generation quality while maintaining computational efficien...