SCOLIA 2026

SCOLIA 2026, the Second International Workshop on Scholarly Information Access, will take place at ECIR 2026 in Delft, The Netherlands. The aim of the SCOLIA (SChOLarly Information Access) workshop, following the successful BIR workshop series and SCOLIA 2025, is to bring together researchers and practitioners from Information Retrieval (IR), Natural Language Processing (NLP), and Scientometrics/Bibliometrics who are working on the analysis of scientific/scholarly documents. The workshop has a broader scope than the previous BIR workshop series. Bibliometrics and Scientometrics are concerned with all quantitative aspects of information and academic literature, which naturally make them interesting for IR research, in particular when it comes to academic search, recommendation, and other domains in which citations play a central role, for example, legal and patent retrieval. 

As a successor of the Bibliometric-enhanced IR (BIR) workshop series at ECIR the SCOLIA workshop recognises the growing importance of fields such as generative AI and NLP for both the Scientometrics and the IR communities. While maintaining the original focus on intersecting the fields of IR with Scientometrics/Bibliometrics, we open the discussion to invite works utilising advanced NLP and AI technologies for academic information access. 

Keynote 

Ingo Frommholz and Libo Ren (Modul University Vienna, Austria): "Fake Science" and Information Overload in Academia – Challenges and Opportunities for Information Retrieval Research

Abstract: Scientific communication is experiencing unprecedented growth, with publication volumes increasing at a scale that overwhelms researchers’ capacity to process and evaluate information. This information overload is not only a byproduct of legitimate scholarly activity but is increasingly driven by low-quality and even fraudulent content. Alongside rigorous, well-designed studies, the scholarly record is also populated by weak methodologies, poorly vetted results, and intentional manipulation. The rise of AI-accelerated publishing, paper mills, tortured phrases, and other forms of “fake science” intensifies this problem, creating massive noise and undermining the reliability of academic information systems.

For the Information Retrieval (IR) community, this poses both critical challenges and unique opportunities. On the one hand, information overload and quality degradation pose a challenge that needs to be addressed more directly by models that, traditionally, are mainly considering topical relevance. On the other hand, advances in AI, NLP, and bibliometric-enhanced IR offer promising directions for filtering, ranking, and contextualising scholarly information. In this talk, we will examine the evolving problem of fake science and its role in driving information overload. We will outline recent developments in scholarly information access, highlight open research problems — from detecting low-quality and fraudulent content to designing veracity-aware retrieval and recommendation models — and discuss how IR research can contribute to ensuring that high-quality knowledge remains discoverable, trustworthy, and actionable in an era of overwhelming information abundance.

Topics

SCOLIA addresses current research issues regarding the broad scope of scholarly information access in the age of retrieval-augmented generation (RAG) and GenAI. Submissions should discuss, but are not limited to, the following topics 

• Construction of scholarly information access systems for tasks such as search, recommendation, or conversational information access, e.g., 

  • Chatting with papers via chatbots

  • Bibliometrics & Scientometrics and IR

  • Finding relevant papers/authors for a literature review

  • Identifying expert reviewers for a given submission

  • Information extraction, text mining and parsing of scholarly literature

  • Recommendation of citations based on the context

  • Discourse modelling and argument mining

  • Retrieval-augmented Generation for LLM-enhanced academic search and recommendation

  • Challenges and opportunities for scholarly information access coming from GenAI and LLMs.
    
    

• Evaluation of scholarly information access systems, e.g., 

  • Quantification of the suitability of the output produced by an LLM

  • Evaluation challenges of generative AI and LLMs for scholarly texts and references

  • Simulated users.

• User Models and Collections, e.g.,

  • Understanding information-seeking behaviour and HCI in academic search

  • Modelling the multifaceted nature of scientific information interaction

  • Building test collections.

•   Pre- and Post-Publication Quality Insurance and Scientific Integrity, e.g., 

  • Filtering high-quality research papers, e.g., in preprint servers

  • Tracking and taming error propagation in the scientific record or scientific misbehaviour

  • Detecting "Fake Science", low quality or automatically generated papers

  • Measuring the degree of plagiarism in a paper

  •  Flagging predatory conferences and journals.

We especially invite descriptions of running projects and ongoing work as well as contributions from industry. Papers that investigate multiple themes directly are especially welcome.

Submission Details

All submissions must be written in English following the CEURART 1-column paper style (6 pages (short paper), 12 pages (full paper), please see below) and should be submitted as single-blind PDF files to EasyChair. 

In addition to regular research papers we encourage the submission of shared task proposals (4 pages). Shared tasks are to be presented at SCOLIA 2026 and carried out so that participants’ results can be presented at SCOLIA 2027 in a dedicated session. Proposals should contain a brief discussion the tasks to be carried out highlighting their connection to SCOLIA’s goals, artefacts expected to be submitted by participants, the evaluation setup including datasets and measures, a preliminary timeline as well as details on organisers.

All submissions will be reviewed by at least two independent reviewers. Please be aware of the fact that at least one author per paper needs to register for the workshop and attend the workshop to present the work. In case of no-show the paper (even if accepted) will be deleted from the proceedings AND from the program. 

CEURART: http://ceur-ws.org/Vol-XXX/CEURART.zip, Overleaf template of CEURART: Template for submissions to CEUR Workshop Proceedings (CEUR-WS.org) - Overleaf, Online LaTeX Editor

Submission via EasyChair: https://easychair.org/conferences/?conf=scolia2026

Page limits:

• Full paper: 12 pages excluding references

• Short paper: 6 pages excluding references

• Shared task proposal: 4 pages excluding references

Workshop proceedings will be deposited online in the CEUR workshop proceedings publication service (ISSN 1613-0073) - this way the proceedings will be permanently available and citable (digital persistent identifiers and long-term preservation).