Search papers, labs, and topics across Lattice.
IRIS Lab
3
0
4
2
Evidence-aware retrieval evaluation can change rankings but doesn't guarantee improved answer quality or retriever training, revealing a nuanced relationship between evaluation methods and downstream utility.
Contrastive scoring is key to the success of anchor-based reranking, but the complexity of anchor design may be overhyped, especially with stronger retrievers.
One-third of documents that seem useless to static readers are actually critical for guiding agentic search, revealing a fundamental disconnect in retrieval utility assessments.