KEIR @ ECIR 2025: The Second Workshop on Knowledge-Enhanced Information Retrieval

TL;DR

KEIR @ ECIR 2025 addresses the limitations of pretrained language models in information retrieval by promoting knowledge-enhanced approaches that access external information such as knowledge graphs, external corpora, and LLM-generated knowledge. The paper proposes a dedicated workshop as a forum for discussing knowledge-enhanced retrieval models, retrieval-augmented generation, and knowledge-aware LLMs, along with data collection, evaluation methodologies, and ethical considerations. It outlines a half-day in-person format with keynote talks, oral/poster sessions, and panels, with a 6-12 page CFP and potential LNCS publication, plus possible talks at the main ECIR conference. By bringing together academia and industry, the workshop aims to accelerate practical progress in knowledge integration for IR, RecSys, and NLP, and to foster collaboration around RAG, KGs, and trustworthy knowledge-enabled systems.

Abstract

Pretrained language models (PLMs) like BERT and GPT-4 have become the foundation for modern information retrieval (IR) systems. However, existing PLM-based IR models primarily rely on the knowledge learned during training for prediction, limiting their ability to access and incorporate external, up-to-date, or domain-specific information. Therefore, current information retrieval systems struggle with semantic nuances, context relevance, and domain-specific issues. To address these challenges, we propose the second Knowledge-Enhanced Information Retrieval workshop (KEIR @ ECIR 2025) as a platform to discuss innovative approaches that integrate external knowledge, aiming to enhance the effectiveness of information retrieval in a rapidly evolving technological landscape. The goal of this workshop is to bring together researchers from academia and industry to discuss various aspects of knowledge-enhanced information retrieval.