Attention-based models can retrieve evidence intrinsically by using decoder attention to score and reuse their own pre-encoded chunks, outperforming separate retrieval pipelines on QA benchmarks.
ColBERT: Efficient and effective passage search via con- textualized late interaction over bert
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
CAR reranks documents in RAG by promoting those that increase generator confidence (via answer consistency sampling) and demoting those that decrease it, yielding NDCG@5 gains on BEIR datasets that correlate with F1 improvements.
citing papers explorer
-
Retrieval from Within: An Intrinsic Capability of Attention-Based Models
Attention-based models can retrieve evidence intrinsically by using decoder attention to score and reuse their own pre-encoded chunks, outperforming separate retrieval pipelines on QA benchmarks.
-
CAR: Query-Guided Confidence-Aware Reranking for Retrieval-Augmented Generation
CAR reranks documents in RAG by promoting those that increase generator confidence (via answer consistency sampling) and demoting those that decrease it, yielding NDCG@5 gains on BEIR datasets that correlate with F1 improvements.