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

2025-11-01

AI Summary

Late-interaction retrieval models (e.g., ColBERT) achieve strong performance in cross-domain, reasoning-intensive, and cross-modal retrieval tasks, yet suffer from low efficiency, poor system integrability, and a lack of real-world deployment feedback; moreover, research remains fragmented and industry engagement is limited. This workshop establishes the first dedicated forum for late-interaction and multi-vector retrieval, emphasizing empirical knowledge sharing on fine-grained token-level matching—particularly early-stage explorations, production deployment experiences, and candid reporting of negative or anomalous results. By fostering deep academia–industry collaboration, it aims to drive tangible advances in retrieval efficiency, system usability, and applicability to emerging scenarios (e.g., cross-modal reasoning). The initiative seeks to cultivate a highly interactive, practice-oriented international research community centered on deployable, scalable late-interaction retrieval technologies.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Computer Vision: Image and Video Retrieval
• Knowledge Representation and Reasoning: Applications

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs

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.

Problem

• Addressing efficiency and integration challenges in late interaction retrieval methods
• Exploring novel applications like reasoning-based and cross-modality retrieval
• Bridging fragmented research efforts between academic and practitioner communities

Innovation

• Late interaction uses token-level representations for retrieval
• It enhances generalization in out-of-domain settings
• It applies to reasoning-based and cross-modality retrieval