7 papers
Quantifying and Expanding the Theoretical Capacity of Late-Interaction Retrieval Models
Julian Killingback, Varad Ingale, Hamed Zamani +1
Late-interaction retrieval models that use the MaxSim similarity function have shown strong empirical performance, often outperforming single-vector dense and sparse retrieval mode…
A Unified Model and Document Representation for On-Device Retrieval-Augmented Generation
Julian Killingback, Ofer Meshi, Henry Li +2
Traditional Retrieval-Augmented Generation (RAG) approaches generally assume that retrieval and generation occur on powerful servers removed from the end user. While this reduces l…
Scaling Laws for Embedding Dimension in Information Retrieval
Julian Killingback, Mahta Rafiee, Madine Manas +1
Dense retrieval, which encodes queries and documents into a single dense vector, has become the dominant neural retrieval approach due to its simplicity and compatibility with fast…
Benchmarking Information Retrieval Models on Complex Retrieval Tasks
Julian Killingback, Hamed Zamani
Large language models (LLMs) are incredible and versatile tools for text-based tasks that have enabled countless, previously unimaginable, applications. Retrieval models, in contra…
ExPerT: Effective and Explainable Evaluation of Personalized Long-Form Text Generation
Alireza Salemi, Julian Killingback, Hamed Zamani
Evaluating personalized text generated by large language models (LLMs) is challenging, as only the LLM user, i.e., prompt author, can reliably assess the output, but re-engaging th…
Hypencoder: Hypernetworks for Information Retrieval
Julian Killingback, Hansi Zeng, Hamed Zamani
Existing information retrieval systems are largely constrained by their reliance on vector inner products to assess query-document relevance, which naturally limits the expressiven…