4 papers
Reranking with Compressed Document Representation
Hervé Déjean, Stéphane Clinchant
Reranking, the process of refining the output of a first-stage retriever, is often considered computationally expensive, especially with Large Language Models. Borrowing from recen…
RANa: Retrieval-Augmented Navigation
Gianluca Monaci, Rafael S. Rezende, Romain Deffayet +5
Methods for navigation based on large-scale learning typically treat each episode as a new problem, where the agent is spawned with a clean memory in an unknown environment. While…
PISCO: Pretty Simple Compression for Retrieval-Augmented Generation
Maxime Louis, Hervé Déjean, Stéphane Clinchant
Retrieval-Augmented Generation (RAG) pipelines enhance Large Language Models (LLMs) by retrieving relevant documents, but they face scalability issues due to high inference costs a…
Let your LLM generate a few tokens and you will reduce the need for retrieval
Hervé Déjean
In this paper, we investigate how efficiently large language models (LLM) can be trained to check whether an answer is already stored in their parametric memory. We distill an LLM-…