ECIR 2025 Workshops
QPP++ 2025: Query Performance Prediction and its Applications in the Era of Large Language Models (QPP++ 2025) Full-day
Organizers:
Chuan Meng (University of Amsterdam, The Netherlands); Guglielmo Faggioli (University of Padova, Italy); Mohammad Aliannejadi (University of Amsterdam, The Netherlands); Nicola Ferro (University of Padova, Italy); Josiane Mothe (Université de Toulouse, France).
Abstract:
Query performance prediction (QPP) is a key task in information retrieval (IR) and has been studied for over a decade. The task of QPP is defined as estimating search effectiveness without human relevance judgments. In this workshop, we aim to bring together researchers and practitioners from academia and industry to discuss new perspectives on QPP. Amongst the limitations in the existing QPP literature, we can mention little work has focused on (i) predicting the performance of newly emerged large language model (LLM)-based retrievers/re-rankers or of generative AI systems, (ii) leveraging LLM to model QPP, (iii) investigating concrete applications of QPP, (iv) exploring QPP in the context of multi-modal content, and (v) exploring multilingual QPP. Those are examples of topics that we encourage authors to contribute to in this workshop.
The Second Search Futures Workshop at ECIR’25 Full-day
https://searchfutures.github.io/
Organizers:
Charlie Clarke (University of Waterloo, Canada); Paul Kantor (Rutgers University, USA); Adam Roegiest (Zuva, Canada); Ian Soboroff (National Institute of Standards and Technology, USA); Johanne Trippas (RMIT University, Australia); Zhaochun Ren (Leiden University, The Netherlands).
Abstract:
The Information Retrieval (IR) field is undergoing rapid transformation, charged by advancements in Artificial Intelligence (AI) and evolving research practices. As IR redefines its role within the broader computing and information sciences, this is a crucial moment to reflect as the European Conference on Information Retrieval (ECIR) community on its future direction. Critical discussions will focus on the challenges and opportunities ahead, and the emerging research questions reshaping how we understand and approach search technologies. This second Search Futures workshop will serve as a forum for the IR community to exchange ideas, voice concerns, and propose bold strategies to strengthen and move the field forward.
The 5th Workshop on Reducing Online Misinformation through Credible Information Retrieval (ROMCIR 2025) Half-day
Organizers:
Udo Kruschwitz (University of Regensburg, Germany); Marinella Petrocchi (Institute of Informatics and Telematics, National Research Council, Italy); Marco Viviani (University of Milano-Bicocca, Italy).
Abstract:
The 5th Workshop on Reducing Online Misinformation through Credible Information Retrieval (ROMCIR 2025) aims to foster discussion and explore potential solutions to online information disorder by examining both subjective and objective factors that influence the credibility and truthfulness of information. These factors will be analyzed as essential elements of relevance within Information Retrieval (IR) systems. As misinformation has been addressed from various angles in recent years—such as fake news detection, bot detection, and truthfulness assessment—this workshop at ECIR 2025 seeks to contextualize these challenges within the field of IR while leveraging insights from related domains of Artificial Intelligence, including Natural Language Processing (NLP), Natural Language Understanding (NLU), Computer Vision, Machine Learning, and Deep Learning.
Eighth International Workshop on Narrative Extraction from Texts (Text2Story’25) Half-day
https://text2story25.inesctec.pt/
Organizers:
Ricardo Campos (INESC TEC; University of Beira Interior, Portugal); Alípio Jorge (INESC TEC; University of Porto, Portugal); Adam Jatowt (University of Innsbruck, Austria); Sumit Bhatia (Media and Data Science Research Lab, Adobe, India); Marina Litvak (Shamoon Academic College of Engineering, Israel).
Abstract:
For seven years, the Text2Story Workshop series has fostered a vibrant community dedicated to understanding narrative structure in text, resulting in significant contributions to the field and developing a shared understanding of the challenges in this domain. While traditional methods have yielded valuable insights, the advent of Transformers and LLMs have ignited a new wave of interest in narrative understanding. In the eighth edition of the Text2Story workshop, we propose to go deeper into the role of LLMs in narrative understanding exploring the issues involved in using LLMs to unravel narrative structures, while also examining the characteristics of narratives generated by LLMs. By fostering dialogue on these emerging areas, we aim to identify the wide-ranging issues related to the narrative extraction task and continue the workshop’s tradition of driving innovation in narrative understanding research.
Geographic Information Extraction from Texts (GeoExT) Half-day
https://geo-ext.github.io/GeoExT2025/
Organizers:
Xuke Hu (German Aerospace Center – DLR, Germany); Ross Purves (University of Zurich, Switzerland); Ludovic Moncla (University of Lyon, INSA, CNRS, UCBL, LIRIS, UMR, France); Jens Kersten (German Aerospace Center – DLR, Germany); Anna Kruspe (Munich University of Applied Sciences, Germany).
Abstract:
A wealth of unstructured texts holds geographic insights that are valuable across various domains. Despite recent significant advances in methods for extracting geographic information from texts, challenges remain regarding the reliability and applicability of these techniques. This workshop is dedicated to addressing these challenges by fostering discussions on recent breakthroughs, novel approaches, and conceptual innovations in geographic information extraction.
The Second Workshop on Knowledge-Enhanced Information Retrieval (KEIR @ ECIR 2025) Half-day
https://keir-ecir2025.github.io/
Organizers:
Zihan Wang (University of Amsterdam, The Netherlands); Jinyuan Fang (University of Glasgow, UK); Giacomo Frisoni, University of Bologna, Italy); Zhuyun Dai (Google DeepMind); Zaiqiao Meng (University of Glasgow, UK); Gianluca Moro (University of Bologna, Italy); Emine Yilmaz, (University College London, UK).
Abstract:
Pretrained language models (PLMs) like BERT and GPT-4 have become foundational to modern information retrieval (IR) systems. However, existing PLM-based IR models primarily rely on knowledge learned during training for predictions, limiting their ability to access and incorporate external, up-to-date, or domain-specific information. Consequently, current IR systems struggle with semantic nuances, contextual relevance, and domain-specific challenges. This workshop (KEIR @ ECIR 2025) serves 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. Our goal is to bring together researchers from academia and industry to explore various aspects of knowledge-enhanced information retrieval.
Open Web Search (WOWS) Half-day
https://opensearchfoundation.org/wows2025
Organizers:
Sheikh Farzana (German Aerospace Center, Germany), Maik Fröbe (Friedrich-Schiller-Universität Jena, Germany), Michael Granitzer (University of Passau, Germany), Gijs Hendriksen (Radboud University, The Netherlands), Djoerd Hiemstra (Radboud University, The Netherlands), Martin Potthast (University of Kassel, hessian.AI, and ScaDS.AI, Germany), Arjen de Vries (Radboud University, The Netherlands); Saber Zerhoudi (University of Passau, Germany).
Abstract:
The web is an important resource for many services and applications. However, only a few large organizations have the computational and technical capabilities to process the web at scale. The Second International Workshop on Open Web Search (WOWS) aims to promote and discuss ideas and approaches to open up the web search ecosystem so that small research groups and young startups can leverage the web to foster an open and diverse search market. Therefore, the workshop has two calls: (1) for scientific contributions and (2) for the WOWS-Eval shared task that aims to gain practical experience with joint, cooperative evaluation of search engines by enriching the Open Web Index (OWI) with relevance judgments cooperatively transferred from existing TREC-style test collections. The first call aims for scientific contributions to building collaborative search engines, including collaborative crawling, collaborative search engine deployment, collaborative search engine evaluation, and collaborative use of the web as a resource for researchers and innovators. The second call aims to gather open-source prototypes for relevance transfer to the Open Web Index and to collect relevance judgments that can subsequently guide the development of retrieval systems on the Open Web Index.
Workshop on Evaluation of Retrieval-Augmented Generation Systems (Eval4RAG) Half-day
Organizers:
Eugene Yang (Human Language Technology Center of Excellence, Johns Hopkins University, USA); Ronak Pradeep (University of Waterloo, USA); Dake Zhang (University of Waterloo, USA); Sean MacAvaney (University of Glasgow, UK); Maria Maistro (University of Copenhagen, Denmark); Mohammad Aliannejadi (University of Amsterdam, The Netherlands).
Abstract:
As generative models increase the number of parameters, constantly fine-tuning them to incorporate new information into the generated output is cost-prohibitive. A popular approach for incorporating external knowledge into the model response is Retrieval-Augmented Generation (RAG). A number of evaluation campaigns, shared tasks, and collections have attempted to benchmark this new style of system combination, which has led to a diverse set of tasks, systems, and evaluation approaches.
First International Workshop on Scholarly Information Access (SCOLIA 2025) Half-day
https://sites.google.com/view/bir-ws/scolia-2025
Organizers:
Ingo Frommholz (University of Wolverhampton, UK); Philipp Mayr (GESIS – Leibniz Institute for the Social Sciences, Germany); Guillaume Cabanac (University of Toulouse, France); Suzan Verberne (Leiden University, The Netherlands); Christin Kreutz (TH Mittelhessen and Herder Institute for Historical Research on East Central Europe, Germany).
Abstract:
The first workshop on Scholarly Information Access (SCOLIA) takes place at ECIR 2025 as a half-day workshop. The workshop is building upon and following up on the long series of the Bibliometric-enhanced Information Retrieval (BIR) workshops at ECIR. SCOLIA addresses research topics related to academic search and recommendation, at the intersection of Information Retrieval, Natural Language Processing (including generative AI), and Bibliometrics/Scientometrics. As an interdisciplinary and intersectoral scientific event, addressing an ever-growing topic investigated by both academia and industry, SCOLIA brings together researchers and practitioners from the aforementioned communities. The interactive format fosters engagement of all participants and fruitful discussions. The outcome of the workshop will reflect the current state and identify future research questions.