October 2026 - Corpora

Call for abstracts | LLMs and the Social Sciences and Humanities: Research, Resources and Infrastructures
by Rui Sousa Silva 14 Oct '26

14 Oct '26

CALL FOR ABSTRACTS LLMs and the Social Sciences and Humanities: Research, Resources and Infrastructures November 30, 2026 – Faculty of Engineering, University of Porto, Portugal https://llmssh.events.up.pt/ Large Language Models (LLMs) are creating new opportunities for research in the Social Sciences and Humanities (SSH), while raising important questions about research methodology, data, interpretation, reliability, integrity, ethics, and reproducibility. From analysing historical documents and cultural artefacts to studying social phenomena, language, and human behaviour, LLMs are now opening new avenues for research while challenging established paradigms to knowledge production. How can SSH researchers meaningfully integrate LLMs into their research? What can these models contribute to established research methods, and what are their limitations? What resources, tools, and research infrastructures are needed, alongside critical thinking, to support reliable, transparent, and reproducible LLM-based research? This one-day symposium aims to bring together researchers working across the Social Sciences and Humanities to share experiences, present ongoing work, discuss methodological challenges, and explore emerging research opportunities involving LLMs. It will also introduce participants to CLARIN, the European research infrastructure for language resources and technologies, and PORTULAN CLARIN, its Portuguese national infrastructure, highlighting how these infrastructures can support research involving language data, digital resources, and LLM-based methods. We welcome contributions from researchers at all career stages and from a broad range of SSH disciplines. Contributions are encouraged both from researchers already working with LLMs and from those critically examining their potential, limitations, and implications for SSH research. Topics of Interest Topics of interest include, but are not limited to: * LLMs in SSH research: Applications of LLMs in the social sciences and the humanities, including linguistics, history, philosophy, political science, sociology, communication, psychology, digital humanities, cultural heritage, and related fields. * LLMs as research tools: Using LLMs for qualitative and quantitative analysis, text interpretation, classification, annotation, information extraction, summarisation, and other research tasks. * Research methodology and evaluation: Methodological frameworks, evaluation strategies, validation, reproducibility, and the reliability of LLM-assisted research. * LLMs, language, and meaning: Language understanding, interpretation, discourse analysis, multilingualism, cultural context, and knowledge representation. * Data and research resources: Corpora, datasets, digital collections, data curation, synthetic data, and the role of language resources in LLM-based research. * Ethical and societal implications: Bias, fairness, privacy, transparency, accountability, research integrity, and the broader societal consequences of LLM adoption. * Critical perspectives on LLMs: Theoretical and conceptual perspectives on the capabilities, limitations, and epistemological implications of LLMs. * Research infrastructures and open science: The role of CLARIN, PORTULAN CLARIN, and other research infrastructures in supporting resource discovery, data sharing, sustainable research practices, and reproducibility. * LLMs and research practice: Changes to scholarly workflows, interdisciplinarity, human–AI collaboration, and the role of researchers in LLM-assisted knowledge production. We particularly welcome work that connects substantive SSH research questions with methodological reflection, empirical evidence, or the use of research resources and infrastructures. Work in progress, preliminary results, case studies, and critical reflections are also encouraged. Submission Guidelines Researchers are invited to submit abstracts describing original research, ongoing projects, methodological contributions, empirical case studies, or conceptual perspectives relevant to the symposium. * Abstract length: 300–500 words * Language: English * Submission format: online submission form * Submission deadline: November 15, 2026 * Notification of acceptance: November 20, 2026 * Submission link: https://forms.gle/iT84kjLVq4ZwaxB96 Submissions should briefly describe the research question or motivation, the approach adopted, and the main findings, expected contributions, or issues to be discussed, as appropriate. Accepted contributions will be presented as short oral presentations, followed by discussion. The symposium aims to foster interdisciplinary exchange and welcomes contributions that may not fit traditional computer science, NLP, or SSH conference formats. About the Symposium The symposium is organised in connection with CLARIN, the European Common Language Resources and Technology Infrastructure. Alongside research presentations and invited talks, the programme will introduce participants to CLARIN and PORTULAN CLARIN, their resources and services, and their potential to support research involving LLMs. A dedicated session will explore how research infrastructures can contribute to more transparent, reusable, and sustainable SSH research. We invite the SSH research community to contribute to the discussion and help shape the future of LLM-based research. Organising committee: * Henrique Lopes Cardoso, FEUP / LIACC * Rui Sousa-Silva, FLUP / CLUP * Gil Rocha, FEUP / LIACC * David Freitas, FEUP / LIACC Contact: hlc(a)fe.up.pt<mailto:hlc@fe.up.pt>

1 0

Call for Participation: Preconference on Computational Affective Linguistics at SAS 2027
by krishnapriya.vishnubhotla＠nrc-cnrc.gc.ca 14 Oct '26

14 Oct '26

We invite submissions to the Computational Affective Linguistics (CAL) preconference at the 2027 Annual Conference of the Society for Affective Science (SAS)! This preconference aims to bring together researchers from affective science, psychology, cognitive science, and natural language processing to explore what computational methods can teach us about emotion, and what emotion theory can teach computation. Topics of interest may include, but are not limited to: - Qualitative and quantitative studies of affect and emotion in natural language - Demonstrations of innovative natural language methods for affect and emotion - Data and resources for studying affect in language and communicative modalities - Downstream applications of affective computational linguistics (e.g., AI, health, education) - Ethical and philosophical implications of affective linguistic modeling We invite novel and recent work along two main submission tracks: - Ideas: These submissions showcase a new research idea, proof-of-concept methodology, or theoretical perspectives on the computational understanding of affect and emotion. - Findings: These report new empirical resources, methods, or findings on affect and emotion resulting from a quantitative or qualitative analysis of data. The submission can be one of two types: - Abstracts: at most 300 words - Extended abstracts: up to 2 pages. Authors will have the option to publish extended abstracts on the ACL Anthology. Abstracts are non-archival: they can be published or presented at other conference venues. More information, along with details of submission formatting, can be found at the CAL pre-conference website: https://casworkshop.github.io/cal-sas/about/. Email cas-workshop(a)googlegroups.com with any questions! For submission, visit the SAS pre-conference page: https://society-for-affective-science.org/2027-sas-annual-conference/pre-co…. To diversify content across the preconference and the main SAS conference, we ask that speakers do not submit identical material to both forums. Submissions are due January 11, 2027, with decisions announced by January 19. [Sent on behalf of the 2027 SAS Computational Affective Linguistics Pre-Conference Organizing Committee]

1 0

Call for Abstracts: ICLL27 Workshop on Latin Lexical Semantics
by Andrea Farina 14 Oct '26

14 Oct '26

Dear all, Please find below a call for contributions to the workshop Qualitative and quantitative approaches to Latin lexical semantic variation and change<https://www.universiteitleiden.nl/binaries/content/assets/geesteswetenschap…>, organised by Barbara McGillivray and Andrea Farina (King’s College London) at ICLL27 on Thursday, 10 June 2027. We welcome contributions exploring Latin lexical semantics from philological, corpus-based, and computational perspectives, including research on semantic variation and change across historical periods, genres, registers, and lexical fields. Submission link: https://www.universiteitleiden.nl/icll2027/registration Deadline for abstract submission: 16 November 2026

1 0

PhD scholarships at Marburg University
by daniel.braun＠uni-marburg.de 14 Oct '26

14 Oct '26

The NLP Group at Marburg University (https://responsible-nlp.net/) has two open PhD scholarships in the project "Human-in-Control" (Application deadline: 02.11.2026) Two additional doctoral scholarships, funded by the Hans Böckler Foundation, will be awarded to join the junior research group Human-in-Control: Implementing Employee Co-Determination in the Design, Development, and Deployment of Artificial Intelligence (NFG 033) at the NLP Group of Marburg University. The earliest possible start date is in 2027. Artificial intelligence is leading to profound changes in the world of work. Economically and socially, it has the potential to trigger positive developments. However, its unreflective use also entails risks. While the AI Act represents a first step toward protecting consumers, comparable protection is still largely lacking for employees who work with AI systems. Even modern systems inevitably make mistakes. For this reason, humans are often deployed as a control instance (“human-in-the-loop”). Responsibility for errors then lies with employees, who usually lack the means to influence the systems. The aim of the junior research group is to investigate technical methods and organizational processes that enable employees to exert influence over operational AI systems, thereby safeguarding and improving job quality. Possible research questions that could be addressed within one of the three doctoral projects include: - How can employees’ interests and concerns be incorporated into the design process of AI systems, particularly within requirements engineering? - What technical measures can be taken to strengthen the role of humans in Human-in-the-Loop approaches, ensure sufficient influence over systems, and transform a “human-in-the-loop” into a “human-in-control”? - What organizational measures can be implemented to (a) enhance the quality of work for employees who use AI systems and (b) ensure that they have appropriate influence over the processes, models, and outcomes for which they are responsible? Procedure for the application and selection process: The application deadline for the scholarships is 02 November 2026. Promising applicants will be supported by the academic leadership of the junior research group in revising and, if necessary, adapting their project proposal (exposé) to the group’s thematic focus and requirements. Please contact Daniel Braun in advance to discuss your project. The exposé will then undergo academic review. The scholarships will be awarded for a maximum of three years. This standard funding period may be extended in justified cases. Doctoral candidates receive a monthly (tax free) scholarship of €1,750 (€1,650 basic stipend and €100 research allowance). In addition, a health insurance subsidy of up to €100 and, where applicable, family allowances may be granted. Additionally, you can earn up to 500€ per month by taking over teaching responsibilities in the department. Bringing the total compensation to around €2,250 (tax free). Decisions on the doctoral scholarships are made in accordance with the guidelines of the BMFTR and the selection criteria of the Hans Böckler Foundation (HBS). In addition to an above-average academic degree, applicants must demonstrate socio-political or trade union engagement. Doctoral projects may be conducted in German or English. Please apply with the required documents and an exposé (maximum 10 pages) outlining the proposed project and situating it within the research program of the junior research group. Guidelines for preparing the exposé can be found here. A scientific reference letter is not required at this stage. A B2 certificate in German is mandatory for this position but can be obtained until the start of the scholarship. Applications must be submitted via the online application portal of the Hans Böckler Foundation. More information can be found at: https://responsible-nlp.net/open-positions/

1 0

[First CfP] MultiDems @ EACL 2027: The 1st Multidisciplinary Workshop on NLP for Democracies (MultiDems)
by salim.hafid＠proton.me 14 Oct '26

14 Oct '26

Call for Papers:The 1st Multidisciplinary Workshop on NLP for Democracies (MultiDems) Co-located with EACL 2027 at Athens, Greece on March 9–14, 2027 (Apologies for cross-posting) Recent advances in Natural Language Processing (NLP) and Large Language Models (LLMs) create new opportunities for supporting democratic processes, from large-scale citizen consultation and deliberation to debate summarization, preference aggregation, and access to political information. At the same time, their use raises fundamental questions about fairness, diversity, political representation, transparency, and whose voices and perspectives are amplified or marginalized. The 1st Multidisciplinary Workshop on NLP for Democracies (MultiDems) aims to provide a dedicated forum for research at the intersection of NLP, political science, social science, computational social choice, and related disciplines. We particularly encourage the submission of work that moves beyond predominantly US-centric, monolingual, or two-party settings and studies the linguistic, institutional, and political diversity of democratic systems worldwide. Topics of Interest Topics include, but are not limited to: - Social choice and computational social choice in NLP - Agent-in-the-loop and AI-assisted deliberation - Summarization or moderation of political debates, deliberations and citizen consultations - Preference inference and aggregation of citizens’ preferences from natural language - Fairness and bias in political text classification and NLP systems - Multilingual NLP for democratic systems, including multilingual and multi-party contexts - Critical evaluation of AI and NLP systems used in democratic processes - Representation of diverse, minority, and critical voices in AI systems - NLP for participatory and deliberative democracy - Political and parliamentary NLP - Argument mining and opinion aggregation in democratic settings - Evaluation methods and benchmarks for democratic applications of NLP - Human-centered and participatory approaches to AI for democracy - Ethical, societal, and institutional implications of deploying NLP and LLM systems in democratic contexts We particularly encourage interdisciplinary work bringing together NLP with political science, sociology, computational social science, computational social choice, HCI, public policy, law, or related fields. In addition to conventional research papers, we welcome position and conceptual papers, methodological contributions, negative results, datasets and resources, evaluation studies, critical analyses, and interdisciplinary empirical work. Submission Types MultiDems will accept both archival and non-archival submissions. Archival long papers: up to 8 pages of content, excluding references and appendices. Archival short papers: up to 4 pages of content, excluding references and appendices. Archival submissions must describe original work that has not been published elsewhere and, if accepted, will appear in the workshop proceedings. Archival submissions require one author to volunteer as a potential reviewer. Potential reviewers will only be contacted if the existing reviewer pool is not large enough for the number of submissions. Non-archival extended abstracts: up to 4 pages, excluding references. These submissions provide an opportunity to present and discuss work without publication in the workshop proceedings, including relevant work published or accepted elsewhere where permitted by the original venue. Both long and short submissions may contain technical, empirical, theoretical, conceptual, or critical contributions. All submissions must use the official ACL formatting templates. Papers will be submitted through OpenReview and will go through a double-blind review process. MultiDems will accept: - Direct submissions, reviewed by the workshop Program Committee; and - Papers previously reviewed through ACL Rolling Review (ARR), which may be committed to the workshop through OpenReview. For direct submissions, we will seek reviewers across disciplinary backgrounds and, where appropriate, aim to combine NLP/computer-science and social-science perspectives in the review process. Double Submission Policy Papers submitted to the archival track must not have been previously published and must not be under review at any other venue (conference, workshop, or journal) at the time of submission. Submissions that are found to be under review elsewhere, or that substantially overlap with work published or under review elsewhere, will be desk-rejected. Shared Task: Summarization of Citizen Consultations MultiDems will also host an associated shared task on Text Summarization for Online Citizen Consultations. Online consultations enable large-scale democratic participation by collecting citizens' proposals and their votes on public issues (e.g., “We should incorporate the right to clean air into our constitution.”). Turning these contributions into concise, accessible summaries is essential for informing public deliberation and decision-making. Although large language models offer promising opportunities for automating this process, they also raise important questions: Whose proposals are represented? Are minority viewpoints adequately reflected? Does the summary accurately convey both the meaning of proposals and their level of public support? Task: Participants will develop systems that produce concise, coherent summaries of collections of citizen proposals and associated voting data. Each consultation will contain proposals expressed in natural language, a citizen–proposal voting matrix, and the language of the consultation. Systems must generate natural-language summaries in which statements are accompanied by references to the original proposal IDs supporting them. This source-grounded format enables evaluation of both the selection of proposals and their representation in the resulting text, while remaining agnostic to the summarization method. Data & Evaluation: The task introduces a multilingual benchmark based on real-world citizen consultation data across multiple European countries. Beyond conventional summary quality, generated summaries will be evaluated using democratically grounded criteria, including proportional representation of citizens’ preferences, preservation of consensus and disagreement, semantic fidelity to the original proposals, balance in the representation of arguments, and coverage of the opinion space. Systems will be evaluated separately on each dimension, alongside an aggregate score. Importantly, trade-offs between metrics are expected and constitute a central motivation for this shared task: different principles of democratic representation may conflict, and optimizing one criterion may compromise another. The task therefore aims not only to identify effective summarization methods, but also to investigate how alternative approaches navigate these trade-offs. Participation: The competition will be hosted on CodaBench. Participation is open to researchers and practitioners from NLP/ML/AI, computational social choice, political science, and related fields. Teams may participate in the competition without submitting a paper. Participants are also encouraged to submit archival system-description papers presenting their approaches, experimental results, and analyses of democratic evaluation criteria. Selected teams, including those performing particularly well across different evaluation dimensions, will be invited to present their work at the workshop. How to participate in the shared task: Register using this form https://forms.gle/FHe4SGvofhYWAtwZA, you’ll be invited tojoin our google group to stay informed on the Competition launch. Important Dates All deadlines are 11:59 PM Anywhere on Earth (UTC−12). - Direct paper submission deadline: December 23, 2026 - Reviews due: January 13, 2027 - ARR commitment deadline: January 18, 2026 - Notification of acceptance: January 22, 2027 - Camera-ready papers due: February 2, 2027 - Pre-recorded video due: February 12, 2027 - EACL 2027: March 9–14, 2027 - MultiDems workshop date: TBA Dates specific to the shared task are the following: - Data release and Opening of the Codabench competition: early November 2026 - Codabench competition submission deadline : December 3, 2026 - System-description paper submission deadline: December 23, 2026 - Notification of acceptance: January 22, 2027 Invited Speakers We are delighted to welcome: Niclas Boehmer, Assistant Professor, Hasso Plattner Institute, University of Potsdam Researching computational social choice and foundations for fair AI/NLP systems. Judith Möller, Full Professor, Leibniz Institute for Media Research, University of Hamburg Researching algorithms, recommender systems, political communication, and the effects of AI on democratic dynamics. Workshop Format MultiDems is planned as a one-day hybrid workshop, with participation possible both in person at EACL 2027 in Athens and remotely. The program will include invited talks, oral presentations of selected papers, poster presentations, shared-task results, and opportunities for interdisciplinary discussion. Organizers François Yvon — Sorbonne Université / CNRS, France Jean-Philippe Cointet — Sciences Po médialab, France Benjamin Piwowarski — Sorbonne Université / CNRS, France Gaël Lejeune — Sorbonne Université, France Salim Hafid — Sciences Po médialab, France Paul Lerner — Sorbonne Université, France Tanise Ceron — Bocconi University, Italy Eoghan Cunningham — University College Dublin, Ireland Nazanin Shafiabadi — Sorbonne Université, France Pierre-Antoine Lequeu — Sorbonne Université, France Carlo Santagiustina — Inria / Sciences Po médialab, France Laurène Cave — Sorbonne Université, France Workshop website:https://sites.google.com/view/multidems/home PaperSubmission website: TBA CodaBench competition website: TBA Contact - multidems(a)googlegroups.com In case of trouble with the googlegroups email, you can contact the organizers at salim.hafid(a)sciencespo.fr and lequeu(a)isir.upmc.fr.

1 0

First Call for Papers: First Workshop on Linguistic Information for Downstream Applications (LInDA 2027)
by Marion Di Marco 13 Oct '26

13 Oct '26

First Call for Papers: First Workshop on Linguistic Information for Downstream Applications (LInDA 2027) Co-located with EACL 2027 in Athens, Greece (March 13 or 14, 2027) Many languages remain underrepresented in large language models (LLMs), resulting in limited performance on downstream tasks. However, many languages have other resources: dictionaries, grammars, morphological analyses, and other forms of annotated texts. According to Glottolog, about 63% of the world's languages have at least a grammar sketch. Linguistic annotations and resources have gained attention in the NLP community as a means of providing auxiliary information for various NLP tasks, such as machine translation. Linguistic information can help models to better process and represent languages, particularly in low-resource settings where conventional training data are scarce. LInDA brings these two sides together: linguistic information and NLP applications. We want to understand how linguistic resources and annotations can improve downstream tasks, especially for low-resource and underrepresented languages. We also aim to know which types of information are useful, and for which tasks. The workshop has two goals: 1. To evaluate strategies that integrate linguistic information into language models, and to measure their impact on specific applications. 2. To explore how language models can help create or extract linguistic information. We welcome researchers with a background in linguistics, in computer science, or in both. LInDA’s objective is to assess approaches on how languages that lack conventional training data can benefit from linguistic information, particularly for underrepresented languages. The workshop’s central focus is the connection between linguistic annotation and NLP tasks. LInDA invites papers on the use of linguistic information to improve NLP applications, such as machine translation, information retrieval, interlinear gloss generation, morphological analysis, parsing, grammatical annotation, and training of language-specific models, among others. Importantly, each submission must address two points: (1) a linguistic resource or annotation (not necessarily created by the contributors), and (2) its impact on one or more NLP tasks. Papers that cover only one of these points are out of scope. Topics of Interest Topics include, but are not limited to: * Leveraging linguistic resources (e.g., annotations, grammars) to improve NLP tasks, particularly for low-resource languages * Language- and task-specific case studies, as well as more general strategies * Practical NLP applications, such as tools for second language (L2) learners and for educational purposes, based on linguistically informed material * Analyzing the quality of linguistic resources (notably, annotation standardization) and their relevance in NLP downstream tasks * Assessing how linguistic knowledge is represented in pretrained models as a basis for improving their capabilities * Investigating the language proficiency and metalinguistic skills of language models * Ethics of data collection, annotation, and NLP tools for underrepresented languages * Data- and compute-efficient approaches for multi- and mono-lingual modeling, relying on linguistic information for improvement * Cross-lingual transfer by utilizing linguistic knowledge that supports generalization We note that some papers might deviate from the dual requirements outlined above, for example, position papers and papers discussing the ethical considerations surrounding data collection, annotation, and NLP tool development for underrepresented languages. Paper Types All accepted papers will be presented as talks or posters. Archival papers. We follow the general format and requirements of *ACL conferences. Accepted papers will appear in the workshop proceedings in the ACL Anthology. * Long papers: up to 8 pages of content. They should describe original, completed, and unpublished work. It should include evaluation and analysis where possible. * Short papers: up to 4 pages of content. They should present a focused contribution, such as a small experiment, a negative result, a new resource, or an application. References and appendices do not count toward the page limit. Reviewers are not required to read the appendices. Accepted papers may add one page in the camera-ready version to address the reviews. Non-archival papers. Accepted papers will be presented at the workshop but will not appear in the proceedings. This track is open to extended abstracts (up to 2 pages) on ongoing work, and to work already published elsewhere. Submission format Submissions must follow the two-column ACL format. Please use the official ACL LaTex template<https://github.com/acl-org/acl-style-files><https://github.com/acl-org/acl-style-files>. Submissions must be in PDF. All papers must include a Limitations section after the conclusion. This section does not count toward the page limit. An Ethical Considerations section is optional and also does not count toward the limit. ARR commitment LInDA accepts papers that were reviewed through ACL Rolling Review (ARR). The reviews and meta-review must be available by the ARR commitment deadline. Multiple submissions Following general ACL policy, archival papers must not be under review at another venue during the LInDA review period. We do not accept direct submissions that are under review at ARR, or that overlap with such a submission by more than 25%. Non-archival papers do not have this restriction. Double-blind review Review is double-blind. Papers must not include author names or affiliations. Cite your own work in the third person. Links to code or data must be anonymized. Papers that do not follow these rules may be desk-rejected without review. Important Dates Direct submission deadline: December 15, 2026 Pre-reviewed ARR commitment deadline: December 22, 2026 Notification of Acceptance: January 05, 2027 Camera-ready deadline: January 19, 2027 Website and Information Website: https://linda-workshop.github.io/ Contact: linda2027(a)dlsi.ua.es<mailto:linda2027@dlsi.ua.es> Organizing Committee * Marion Di Marco, Technical University of Munich, Germany * Niyati Bafna, Johns Hopkins University, USA * Aleksei Dorkin, University of Tartu, Estonia * Shu Okabe, CentraleSupélec, Université Paris-Saclay, France * Juan Antonio Pérez-Ortiz, Universitat d'Alacant, Spain * Felipe Sánchez-Martínez, Universitat d'Alacant, Spain * Abishek Stephen, Charles University, Czech Republic * Tsedeniya Kinfe Temesgen, Technical University of Munich, Germany * Alexander Fraser, Technical University of Munich, Germany

1 0

First call for papers: 14th Workshop on Argument Mining and Reasoning
by Kikteva, Zlata 13 Oct '26

13 Oct '26

Call for papers: ArgMining 2027 -- 14th Workshop on Argument Mining and Reasoning The Workshop on Argument Mining (ArgMining) provides a regular forum for presenting and discussing cutting-edge research in argument mining (a.k.a. argumentation mining) for academic and industry researchers. Continuing a series of thirteen successful previous workshops, the 2027 edition welcomes submissions of long papers, short papers, extended abstracts, and PhD proposals. Special theme Building on the previous edition's focus on understanding and evaluating arguments in both human and machine reasoning, ArgMining 2027 places a special emphasis on Argumentation in Agentic and Human-AI Settings. Recent work on multi-agent debate offers new ways to investigate and improve LLM reasoning, while developments in human-AI interactive systems create opportunities to support critical thinking and collaborative decision-making. Both settings are inherently argumentative, as they involve participants advancing and contesting positions. This raises questions about the argumentative properties of interactions among agents and between agents and humans, and how established argumentation frameworks can help inform agentic and human-AI interactions. We welcome research that analyzes these interactions, develops systems to support human reasoning, or uses multi-agent debate for argument mining itself. Topics of Interest Other topics include, but not limited to: * Automatic extraction of textual patterns that describe argument components in human and machine argumentation * Cross-lingual, cross-cultural, and multi-perspective argument mining and reasoning * Argument mining and generation from multi-modal and/or multilingual data * Explainability in argument mining through reasoning * Modelling, assessing, and critically reflecting on the argumentation capabilities of LLMs * Novel benchmarks in argument mining that cater to the recent developments in LLM reasoning as a whole * Guidelines for assessing and documenting the reasoning process(es) reflected in benchmarks * Annotation guidelines, linguistic analysis and argumentation corpora * Real-world applications, e.g., supporting analysis of argument and discourse in the social sciences, education, law, or scientific writing; opinion analysis, argument analysis in meetings, and misinformation detection * Integration of commonsense and domain knowledge into argumentation models for mining and generation * Combination of information retrieval methods with argument mining, e.g., in order to build argumentative (web) search engines * Reflection on ethical aspects and societal impact of argument mining and LLM reasoning For this year's special theme, Argumentation in Agentic and Human-AI Settings, we particularly welcome work on: * Evaluation and analysis of argumentative properties of multi-agent debate * Development of human-AI interactive systems to support human reasoning and critical thinking * Application of established argumentation frameworks to agentic and human-AI interactions * Using multi-agent debate to identify, analyse, and evaluate arguments. We welcome submissions from all areas of application. Submission Types The workshop accepts the following submission types: * Long Papers (archival) * Short Papers (archival) * Extended Abstracts (non-archival) * PhD Proposals (non-archival) Accepted contributions will be presented as oral or poster presentations. Archival Submissions Long paper submissions must describe substantial, original, completed, and unpublished work. Long papers must be at most eight pages, including title, text, figures, and tables. An unlimited number of pages is allowed for references. Two additional pages are allowed for appendices, and an extra page is allowed in the final version to address reviewers’ comments. Short paper submissions must describe original and unpublished work. Please note that a short paper is not a shortened long paper. Short papers must be at most four pages, including title, text, figures, and tables. An unlimited number of pages is allowed for references. One additional page is allowed for the appendix, and an extra page is allowed in the final version to address reviewers’ comments. Non-Archival Submissions Extended abstracts must be at most two pages, including references and an additional page as an appendix for tables/figures describing ongoing projects, interesting pieces of data or results, or already published work. PhD proposals must describe PhD projects being or to be developed within the broad field of natural language argumentation processing. PhD proposals must be at most four pages, including the main research directions or challenges being investigated, the specific contributions made (on the research direction), and the directions for the remaining work. Multiple Submissions Policy ArgMining 2027 will not consider papers simultaneously under review elsewhere. Submissions overlapping significantly (>25%) with active ARR submissions will not be accepted. ARR-reviewed papers are allowed if reviews and meta-reviews are available by the ARR commitment deadline. Submission Format All submissions must follow the two-column ACL style guidelines and templates. Submissions must be electronic and in PDF format. Important Dates * Direct paper submission deadline: December 15, 2026 * Pre-reviewed ARR commitment deadline: December 22, 2026 * Archival paper submission deadline: December 22, 2026 * Notification of acceptance: January 5, 2027 * Camera-ready paper due: January 19, 2027 * Pre-recorded video due: February 12, 2027 * Workshop: March 9–14, 2027 (exact date TBA) Review Policy Long and short papers will follow ACL double-blind review policies. Submissions must be anonymized, including self-references and links. Papers violating anonymity requirements will be rejected without review. Demo descriptions are exempt from anonymization. Best Paper Award ArgMining 2027 will present a Best Paper Award to recognize significant contributions to argument mining research. All accepted papers are eligible. Contact and Information Website: https://argmining-org.github.io Email: argmining.org [at] gmail.com Workshop organisers Debanjan Ghosh, Analog Devices Kamila Gorska, University of Liverpool Zlata Kikteva, University of Technology Nuremberg Priya Pitre, Virginia Tech Jodi Schneider, University of Wisconsin-Madison Manfred Stede, University of Potsdam Michiel van der Meer, Leiden University

1 0

Open Corpus Research Group – Starts 28 October (online)
by Brezina, Vaclav 13 Oct '26

13 Oct '26

Dear all, I’m pleased to let you know that The ESRC Centre for Corpus Approaches to Social Science (CASS), Lancaster University is resuming its regular Open Research Group meetings on 28th October, 12–1 pm UK time. These meetings are open to everyone, and we would be delighted to welcome anyone who might be interested. Please feel free to share this invitation with your students or others who may wish to join us. Free registration: https://forms.cloud.microsoft/e/YT5md2fjka More info: https://cass.lancs.ac.uk/open-research-group-starts-28th-october-communicat… This term, we’ll be exploring effective communication with different stakeholders, both academic and non-academic, under the theme Communicating with Confidence. Reading: Olivier, L. (1986). On Acting. London: Weidenfeld and Nicolson. https://openlibrary.org/books/OL2716891M/On_acting Dates: * 28 October * 11 November * 25 November * 9 December Certificates of attendance will be available to registered participants who attend regularly. Best, Vaclav Professor Vaclav Brezina Professor in Corpus Linguistics Co-Director of the ESRC Centre for Corpus Approaches to Social Science Faculty of Humanities, Arts and Social Sciences, Lancaster University Lancaster, LA1 4YD Office: County South, room B46 T: +44 (0)1524 510828 @vaclavbrezina

1 0

Postdoc / Postdoctoral Researcher in NLP and Research Knowledge Graphs (KTS-86)
by Dietze, Stefan 13 Oct '26

13 Oct '26

We are looking for a Postdoctoral Researcher in NLP and Research Knowledge Graphs <https://gesis.jobs.personio.de/job/2838467?language=en> in the department Knowledge Technologies for the Social Sciences (KTS), Team Information and Data Retrieval for the Cologne location by December 01, 2026. ** *Postdoctoral Researcher* *(Salary group 13 TV-L, working time 100%, limited till 31.12.2028, subject to approval)* The department *Knowledge Technologies for Social Sciences (KTS <https://www.gesis.org/en/kts>) conducts research at the intersection of information retrieval, natural language processing, semantic technologies and human information interaction as foundation for innovative web portals and platforms for the search and use of research data. AI is transforming the scientific process across disciplines. In the NFDI4DS project, we develop infrastructures that empower researchers to responsibly adopt AI methods—for example, by establishing fair benchmarking protocols, ensuring transparent evaluation and documentation of AI models and LLMs, and curating a repository of open, reusable AI-based methods, along with related training materials and events. In this context, we are seeking a motivated researcher to coordinate and lead these activities. *Your tasks will be:* * Lead dedicated work packages and a team of researchers within the NFDI4DS <https://www.nfdi4datascience.de/>project including coordination with project partners and supervision of PhD students * Research scholarly information extraction and develop methods for building Research Knowledge Graphs (e.g., GESIS KG <https://data.gesis.org/gesiskg/site/>) * Develop, integrate, and evaluate services, models, and systems using established benchmarks * Advance the NFDI4DS Academy through community engagement, content acquisition (methods, tutorials, training material) and integration with third party infrastructures * Exchange with scientific and user communities and dissemination of project results through publications and workshops at national and international level *Your profile:* * Completed academic university degree (Master’s or equivalent) and completed PhD in computer science, data science, or a related field * Experience in project management (Strong mentoring and communication skills to effectively supervise and support PhD students) * Proven experience in NLP research and knowledge graphs, specifically in the context of scholarly information extraction. * Very good experience in software development with Python, AI-tooling, NLP technologies and database technologies * Very good verbal and written communication skills in English; good knowledge of German desirable Please apply via our Online-application portal until *Nov. 2^nd 2026* application deadline. Our reference number is: *KTS-86* More details; please apply via <https://gesis.jobs.personio.de/job/2838467?language=en <https://gesis.jobs.personio.de/job/2838467?language=en>> -- Prof. Dr. Stefan Dietze Scientific Director Knowledge Technologies for the Social Sciences GESIS - Leibniz Institute for the Social Sciences Web: https://www.gesis.org/en/kts Chair of Data & Knowledge Engineering Heinrich-Heine-University Düsseldorf Web: https://www.cs.hhu.de/en/research-groups/data-knowledge-engineering Phone: +49 (0)221-47694-421 Web: http://stefandietze.net

1 0

[CFP] ACLing 2026 – Extended Deadline: 5 November | NLP & Language-Model Applications Across Disciplines
by Khaled Shaalan 13 Oct '26

13 Oct '26

Dear Colleagues, Submission deadline extended to 5 November 2026. Expanded scope: Language-model applications across disciplines are welcome. ACLing 2026 8th International Conference on AI in Computational Linguistics 25–26 November 2026 | Multi-Site Hybrid Conference 📍 The British University in Dubai (BUiD), Dubai, UAE 📍 Jadara University, Jordan 🌐 Virtual participation worldwide Conference website: https://acling.org/ Submission: https://easychair.org/conferences/?conf=acling2026 CALL FOR PAPERS ACLing 2026 invites researchers, academics, practitioners, and industry professionals to submit original research in computational linguistics, natural language processing (NLP), and the development, evaluation, and application of language models. The conference welcomes both advances in language technologies and interdisciplinary research using pretrained language models, large language models (LLMs), or vision-language models to address problems in other fields. Applications in healthcare, education, cybersecurity, business, engineering, agriculture, and environmental sustainability are encouraged. Application papers do not need to introduce a new language model or linguistic theory. Language models should play a central methodological role, and submissions should present a clear scientific contribution supported by appropriate evaluation. Research on any natural language is welcome, including Arabic, multilingual, cross-lingual, code-switching, and low-resource settings. Papers and presentations must use English; this requirement does not restrict the language studied. ACLing 2026 connects two physical conference hubs with virtual participation through one unified scientific program. Authors may present in Dubai, Jordan, or online, subject to the final program and session allocation. Two Countries. Two Physical Hubs. One International Research Community. IMPORTANT DATES — UPDATED • Paper Submission Deadline: 5 November 2026 • Acceptance Notification: 10 November 2026 • Camera-Ready Submission: 14 November 2026 • Author Registration: 15 November 2026 • Conference: 25–26 November 2026 Rolling review: Submissions are reviewed as they arrive to provide prompt feedback and decisions. Authors are encouraged to submit early. PUBLICATION & RESEARCH VISIBILITY Accepted papers meeting the camera-ready, registration, and presentation requirements will be submitted for publication in Procedia Computer Science (ISSN: 1877-0509), Elsevier, subject to the publisher’s requirements and approval. Publication provides open-access availability on ScienceDirect and a DOI for each article. For current indexing and ranking information, consult the source records linked on the conference website. Previous ACLing proceedings include the 2017, 2018, 2021, 2024, and 2025 editions and are catalogued in DBLP: https://dblp.org/db/conf/acling/index.html OPTIONAL EXTENDED JOURNAL PUBLICATION Authors of accepted papers may submit a substantially extended article to the Computation (MDPI) special issue, Recent Advances on Computational Linguistics and Natural Language Processing—2nd Edition. Eligibility depends on the article’s fit with the special issue’s scope and independent journal peer review. Conference acceptance does not guarantee journal acceptance. A special APC discount is available for ACLing authors; contact the organizing team for details. Journal APCs are separate from conference registration. Details: https://acling.org/call-for-papers/ TOPICS OF INTEREST Topics include, but are not limited to: • Pretrained and Large Language Models: Architecture, Optimization, and Applications • Language-Model Applications Across Disciplines • Generative AI and Emerging Language Technologies • Retrieval-Augmented Generation, Knowledge Grounding, and Information Retrieval • Language-Model Agents, Tool Use, and Multi-Agent Systems • Domain Adaptation, Fine-Tuning, and Efficient Language Models • Language Models for Decision Support and Scientific Discovery • Question Answering and Knowledge Extraction • Statistical and Neural Language Modeling • Machine Translation and Cross-Lingual NLP • Multilinguality, Code-Switching, and Low-Resource Languages • Speech Technologies, Dialogue Systems, and Conversational AI • Vision-Language Models and Multimodal AI • Domain-Specific NLP • Syntax, Parsing, Semantics, Pragmatics, and Commonsense Reasoning • Emotion Recognition and Sentiment Analysis • NLP for Social Media and Computational Social Science • Text Summarization and Natural Language Generation • Text Classification, Topic Modeling, and Document Understanding • Text Mining and Knowledge Discovery • Responsible, Ethical, Interpretable, and Human-Centered AI • Reliability, Robustness, Bias, and Hallucinations in Language Models • Benchmarking, Application Evaluation, and Explainability • Prompt Engineering and Reinforcement Learning for Language Models • AI-Augmented Writing, Reading, and Translation Tools Theoretical contributions, algorithms, architectures, applications, resources, datasets, benchmarks, and evaluation studies are welcome, alongside rigorous surveys and position papers. SUBMISSION & REVIEW • Submit original, unpublished work that is not under consideration elsewhere. • Prepare a complete manuscript using the official ACLing 2026 single-column Word or LaTeX template. • Initial manuscripts must be anonymized for double-blind peer review. • Standard length: 3–8 pages, including figures, tables, and references. • Up to two additional pages are permitted, for a maximum of 10 pages, with an additional charge for pages 9 and 10. • Abstract-only submissions are not accepted. • At least one author must register and present each accepted paper for inclusion in the proceedings. Submit through EasyChair: https://easychair.org/conferences/?conf=acling2026 Templates and submission guidelines: https://acling.org/submission/ CONFERENCE CHAIRS • Prof. Khaled Shaalan — The British University in Dubai, UAE • Prof. Samhaa R. El-Beltagy — New Giza University, Egypt CONTACT Prof. Khaled Shaalan: khaled.shaalan(a)buid.ac.ae Dr. Taher M. Ghazal: taher.ghazal(a)ieee.org Prof. Samhaa R. El-Beltagy: samhaa(a)computer.org General inquiries: ACLing2026(a)gmail.com We look forward to receiving your contributions and welcoming you to ACLing 2026. Please circulate this call among interested colleagues, research groups, students, and professional networks. ACLing 2026 | 25–26 November 2026 Dubai • Jordan • Worldwide Online https://acling.org/

1 0

2026

2025

2024

2023

2022

Corpora October 2026