Learning to Filter Context for RAG (FILCO)

Useful-context identification: Uses lexical and information-theoretic signals to identify genuinely useful portions of retrieved documents, rather than passing everything through.

Context-filter training: Trains a separate filtering model whose only job is to retain useful context at inference time.

Extractive QA wins: Outperforms prior RAG approaches on extractive QA benchmarks, a clean demonstration that context filtering is a high-leverage component.

Modular addition: Slots in between retrieval and generation, making it compatible with any retriever/generator pairing.