Learning to Filter Context for RAG (FILCO)
Free while signed in. Answers cite the passages they came from.
CMU's FILCO improves RAG by training a dedicated model to filter retrieved contexts before they reach the generator.
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.
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack