Decision theory shows that LLM cascades are structurally limited by always incurring the cheap model's cost before deciding to escalate, with the best performance given by the envelope of pairwise cascades rather than fixed chains or many stages.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
Nomic AI produced and open-sourced a reproducible 8192-context English text embedder that exceeds OpenAI Ada-002 and text-embedding-3-small performance on MTEB short-context and LoCo long-context benchmarks.
FedCRF fuses global and local semantics via federated learning, semantic graphs, and contrastive constraints to improve cross-domain recommendations in non-overlapping scenarios.
citing papers explorer
-
Is Escalation Worth It? A Decision-Theoretic Characterization of LLM Cascades
Decision theory shows that LLM cascades are structurally limited by always incurring the cheap model's cost before deciding to escalate, with the best performance given by the envelope of pairwise cascades rather than fixed chains or many stages.
-
Nomic Embed: Training a Reproducible Long Context Text Embedder
Nomic AI produced and open-sourced a reproducible 8192-context English text embedder that exceeds OpenAI Ada-002 and text-embedding-3-small performance on MTEB short-context and LoCo long-context benchmarks.
-
FedCRF: A Federated Cross-domain Recommendation Method with Semantic-driven Deep Knowledge Fusion
FedCRF fuses global and local semantics via federated learning, semantic graphs, and contrastive constraints to improve cross-domain recommendations in non-overlapping scenarios.