LIR: The First Workshop on Late Interaction and Multi Vector Retrieval @ ECIR 2026

TL;DR

This work documents the LIR workshop as a dedicated forum for late-interaction and multi-vector retrieval, addressing the promise of token-level, fine-grained interaction like ColBERT while acknowledging efficiency and integration hurdles. It outlines three aims: foster cross-community collaboration between academia and industry, discuss emerging trends such as multimodal and reasoning-based retrieval, and inspire future joint work. The paper details diverse contribution formats (notes, short and full papers, demos, and technical reports) and a hybrid, interactive format featuring keynotes, paper sessions, and round-table discussions to bridge practical and theoretical insights. By centralizing practical experiences, negative results, and early findings, the workshop seeks to accelerate adoption, improve tooling, and guide research toward scalable, real-world late-interaction systems.

Abstract

Late interaction retrieval methods, pioneered by ColBERT, have emerged as a powerful alternative to single-vector neural IR. By leveraging fine-grained, token-level representations, they have been demonstrated to deliver strong generalisation and robustness, particularly in out-of-domain settings. They have recently been shown to be particularly well-suited for novel use cases, such as reasoning-based or cross-modality retrieval. At the same time, these models pose significant challenges of efficiency, usability, and integrations into fully fledged systems; as well as the natural difficulties encountered while researching novel application domains. Recent years have seen rapid advances across many of these areas, but research efforts remain fragmented across communities and frequently exclude practitioners. The purpose of this workshop is to create an environment where all aspects of late interaction can be discussed, with a focus on early research explorations, real-world outcomes, and negative or puzzling results to be freely shared and discussed. The aim of LIR is to provide a highly-interactive environment for researchers from various backgrounds and practitioners to freely discuss their experience, fostering further collaboration.