Search papers, labs, and topics across Lattice.
Affiliation:
3
0
3
42
Token-level credit assignment can drastically improve the effectiveness of generative document retrieval, leading to better alignment between generation and relevance.
You can boost LLM-based recommendations across completely disjoint domains without sacrificing user privacy by using semantic bridges and federated learning.
Forget retraining: DOME efficiently adapts generative retrieval models to new documents by directly editing the model's docID mapping, achieving comparable performance with 40% less training.
