Home | Call for Papers | Speakers | Program | Organizers |
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.
We invite researchers to submit their latest work to the KEIR @ ECIR 2025 workshop on various aspects of knowledge-enhanced information retrieval, including models, techniques, data collection, and evaluation methodologies. Topics covered will include, but are not limited to:
We invite authors to submit papers written in English. Submissions may range in length from a minimum of 6 pages to a maximum of 12 pages; however, references and supplementary materials may exceed this page count without limitation. In order to facilitate a double-blind review process, authors must ensure that submissions are fully anonymized. Please note that we do not impose a specific anonymity period prior to submission.
The papers (.pdf format) should be submitted using the EasyChair submission system at https://easychair.org/conferences/?conf=keirecir2025. Authors should consult Springer’s authors’ guidelines and use their proceedings templates to prepare the submission. The Microsoft Word and LaTeX versions of the template can be found at https://www.springer.com/gp/computer-science/lncs/conference-proceedings-guidelines. Submissions to KEIR @ ECIR 2025 will be peer-reviewed on the basis of technical quality, relevance to workshop topics, originality, significance, clarity, etc.
We accept submissions of the following types:
Good News: Our KEIR @ ECIR 2025 workshop has been accepted as a post-proceedings volume in Springer's Lecture Notes in Computer Science (LNCS). Accepted papers will have the opportunity to be published in the LNCS series!
Invited Talk 1: The Semantic Gap: Understanding What Large Language Models Still Fail to Understand
Abstract: The unprecedented success of Large Language Models (LLMs) in carrying out linguistic interactions disguises the fact that, on closer inspection, their knowledge of meaning and their inference abilities are still quite limited and different from human ones, especially if we consider the super-human amounts of training data. They generate human-like texts, but still fall short of fully understanding them. I will refer to this as the “semantic gap” of LLMs. They learn highly complex association spaces that correspond only partially to truly semantic and inferential ones. In this talk, I will present current research probing the limits of LLMs on undestanding various kinds of semantic relations, with the aim of investigating the missing links to bridge the gap between LLMs as sophisticated statistical engines and full-fledged semantic agents.
Invited Talk 2: Lexical Representations and Test-time Compute for Knowledge-Enhanced IR
Abstract: In this talk, I will describe some of my recent work on knowledge-enhanced IR from two perspectives: building lexical representations for first-stage retrieval and reranking with reasoning LLMs distilled from DeepSeek-R1. To improve first-stage retrieval, the DyVo model incorporates knowledge of entities and concepts into lexical representations made of wordpieces, whereas the LENS model demonstrates that lexical representations can perform competitively with dense representations across a range of tasks. Given this strong retrieval foundation, I will describe Rank1, a recent model that uses test-time compute to perform reranking by reasoning about a document's relevance.
Time (UTC +2, CEST) | Activity | Presenter |
---|---|---|
9:00 AM - 9:10 AM | Welcome & Opening | Organizers |
9:10 AM - 9:50 AM | Invited Talk 1: The Semantic Gap: Understanding What Large Language Models Still Fail to Understand |
Prof. Alessandro Lenci (University of Pisa) |
9:50 AM - 10:30 AM | Invited Talk 2: Lexical Representations and Test-time Compute for Knowledge-Enhanced IR |
Dr. Andrew Yates (Johns Hopkins University) |
10:30 AM - 11:00 AM | Coffee & Break | - |
11:00 AM - 11:30 AM | Poster Session | - |
11:30 AM - 12:00 AM | Panel Discussion | Organizers |
KEIR @ ECIR 2024: https://keirworkshop.github.io