- Corpora - ELRA lists

CFP: International AIWolf Competition 2026 and AIWolfDial 2026 International Workshop
by Yoshinobu Kano 24 Jun '26

24 Jun '26

Call for Participation: International AIWolf Competition 2026 and AIWolfDial 2026 International Workshop Official Details Page: https://aiwolfdial.github.io/aiwolf-nlp/page/inlg_2026/ [Call for Participation] This is a call for participation for the international competition competing in the automated play of the conversational game "Werewolf," as well as for the peer-reviewed international workshop. We look forward to your participation. [Overview] "The 4th International Workshop on AI Werewolf and Dialog Systems (AIWolfDial2026)" will be held as a co-located workshop with INLG 2026 (19th International Conference on Natural Language Generation) on a date between October 17 and October 21, 2026, in Utrecht, Netherlands. Prior to the workshop, we will host the 2026 International AIWolf Contest Natural Language Track. This tournament is divided into two rounds (1st and 2nd); the results of the 1st round can be used to submit a paper to the INLG main conference, and the results of the 2nd round can be used to submit to the AIWolfDial 2026 workshop. The language for agents in the international competition is English only. [Workshop Overview] This workshop focuses on the integration of dialog systems, natural language processing (NLP), large language models (LLMs), and game AI, with a particular emphasis on their application to the Werewolf game. The Werewolf game is a social deduction game that requires advanced communication skills such as discussion, reasoning, persuasion, and deception, making it an ideal test environment for evaluating the advancement of AI capabilities like coherent dialogue, long-context understanding, consensus building, and logical reasoning. [Shared Task (Contest)] This workshop will host a public international contest for AI agents that play the Werewolf game. Participants are challenged to develop agents capable of not only strategic play but also logical, persuasive, and sometimes deceptive conversation with other AIs. This contest serves as a benchmark for discovering critical challenges and future research directions in the NLP field, while also exploring the limitations of current LLMs. [Hosted Tracks] Turn-Based Track: This is a turn-based track where the agent speaks and acts when a request is received from the server provided by the management. o 5-Player Village (2 Villagers, 1 Seer, 1 Possessed, 1 Werewolf) o 9-Player Village (3 Villagers, 1 Seer, 1 Bodyguard, 1 Medium, 1 Possessed, 2 Werewolves) Anytime Utterance Track: This is a track where the agent can speak at any timing alongside the start signal of each day. There is an upper limit to the number of utterances per day (4 times). o 5-Player Village (2 Villagers, 1 Seer, 1 Possessed, 1 Werewolf) [Important Dates (Shared Task)] The schedule for this tournament is divided into a 1st and 2nd round, as shown below. A connection check will be conducted prior to the main tournament. During the connection check, you must verify that you can connect to the official competition server and run the game normally. Teams whose normal connection and game execution are confirmed on the server side will advance to the main tournament. The deadlines are as shown below. While a separate final tournament will not be held, top teams may be selected based on subjective evaluations and win rates from the main tournament results, and statistics may be compiled solely for these top teams by extracting the main tournament logs of matches played among them. Note: Deadlines related to papers are included below; please refer to this schedule from each page on this website. All dates are in AoE. 1st Round (For INLG Main Conference) o July 4, 2026: Registration deadline for "1st + 2nd" participating teams / Connection check deadline o From July 6, 2026: 1st Round Main Tournament (Online matches) o July 10, 2026: Return of 1st Round results o July 15, 2026: INLG main conference paper deadline 2nd Round (For AIWolfDial 2026 Workshop) o August 1, 2026: Registration deadline for "2nd only" participating teams / 2nd round connection check deadline o From August 3, 2026: 2nd Round Main Tournament (Online matches) o August 10, 2026: Return of 2nd Round results o From August 15, 2026: AIWolfDial 2026 workshop paper deadline (After INLG main conference acceptance notification / Submissions are allowed even if rejected from main) o September 7, 2026: Notification of acceptance o September 15, 2026: Camera-ready manuscript deadline o October 17 - October 21, 2026: AIWolfDial 2026 Workshop / INLG 2026 Conference (Utrecht) [Further Information] Please check here for detailed competition rules and specifics regarding the implementation of AIWolf agents. o Official Details Page: https://aiwolfdial.github.io/aiwolf-nlp/page/inlg_2026/ o Contest Registration Form: https://forms.gle/53MJBSaLTe6xDw5o6 o Past Competition Logs: https://aiwolfdial.github.io/aiwolf-nlp-viewer -- Yoshinobu Kano, Ph.D. Professor, Research Fellow Faculty of Informatics, Shizuoka University personal webpage: http://kanolab.net/kano/ e-mail: kano(a)kanolab.net kano(a)inf.shizuoka.ac.jp

1 0

INLG 2026 second call for papers - Submissions are open
by Emiel van Miltenburg 24 Jun '26

24 Jun '26

Dear Corpora List members, It is my pleasure to announce the second Call for Papers for INLG 2026, to be held in Utrecht. Program chairs will be Laura Perez, Guanyi Chen, and myself. We have a great team of local organizers, chaired by Albert Gatt. NEW INFORMATION We now have two submission venues: * Direct submissions: https://openreview.net/group?id=aclweb.org/INLG/2026/Conference_Direct_Subm… * ARR commitments: https://openreview.net/group?id=aclweb.org/INLG/2026/Conference_ARR_Commitm… Please also note that we have a NON-ARCHIVAL track as well this year, for work-in-progress and papers published elsewhere. Hopefully this will help authors develop and publicise their important work. Direct link to the website: https://2026.inlgmeeting.org/ —————————————————————————————————————————————————————— 19th International Natural Language Generation Conference INLG 2026 We invite the submission of long and short papers, as well as system demonstrations, related to all aspects of Natural Language Generation (NLG), including data-to-text, concept-to-text, text-to-text and vision-to-text approaches. Accepted papers will be presented as oral talks or posters. The event is organized under the auspices of the Special Interest Group on Natural Language Generation (SIGGEN) of the Association for Computational Linguistics (ACL). The event will be held from October 17 to October 21, 2026. INLG 2026 will be hosted by Utrecht University in Utrecht, the Netherlands. The conference will be taking place before EMNLP (in Budapest, Hungary, from October 24th to October 29th, 2026). IMPORTANT DATES All deadlines are Anywhere on Earth (UTC-12) Regular paper submission deadline: July 15, 2026. System demo paper submission deadline: July 15, 2026. ARR commitment to INLG deadline: August 5, 2026. Notification: August 15, 2026 Non-archival submission deadline: August 22, 2026. Camera ready: September 7, 2026 Conference: October 17 - October 21, 2026 Topics INLG 2026 solicits papers on any topic related to NLG. General topics of interest include, but are not limited to: - Large Language Models (LLMs) for NLG - Evaluation and error analysis of NLG systems - Explainability in and Trustworthiness of NLG systems - Generalizability of NLG systems - Bias and fairness in NLG systems - Reasoning models for NLG - Affect/emotion generation - Analysis and detection of automatically generated text - Cognitive modeling of language production - Computational efficiency of NLG models - Corpora and resources for NLG - Ethical considerations of NLG - Multimedia, multimodality and grounding in generation - NLG and accessibility - NLG in speech synthesis and spoken language models - NLG in dialogue systems and chatbots - NLG for human-robot interaction - NLG for low-resourced languages - NLG for real-world applications - Paraphrasing, summarization and translation - Personalisation and variation in text - Storytelling and narrative generation - Sub-tasks of the classic NLG pipeline - NLG architectures SUBMISSIONS This year’s INLG will have two tracks: an archival track where papers will be published in the ACL Anthology, and a non-archival track for works in progress and papers published elsewhere. Three kinds of papers can be submitted for the archival track: Long papers are most appropriate for presenting substantial research results and must not exceed eight (8) pages of content, plus unlimited pages of ethical considerations, supplementary material statements, and references. The supplementary material statement provides detailed descriptions to support the reproduction of the results presented in the paper (see below for details). The final versions of long papers will be given one additional page of content (up to 9 pages) so that reviewers' comments can be taken into account. Short papers are more appropriate for presenting an ongoing research effort and must not exceed four (4) pages, plus unlimited pages of ethical considerations, supplementary material statements, and references. The final versions of short papers will be given one additional page of content (up to 5 pages) so that reviewers' comments can be taken into account. Demo papers should be no more than two (2) pages, including references, and should describe implemented systems relevant to the NLG community. It also should include a link to a short screencast of the working software. In addition, authors of demo papers must be willing to present a demo of their system during INLG 2026. Next to the standard paper types (surveys, experiments, resource papers, position papers), we also welcome squibs: papers that present an empirical or theoretical issue without necessarily providing a solution. NON-ARCHIVAL TRACK Through the non-archival track, we hope to foster more discussion on current trends in NLG, and to offer a space for researchers to obtain feedback on their current projects. For this track, we welcome two kinds of submissions: - Papers published elsewhere. These may be published either in a journal or at another conference, and should be relevant to the INLG audience. - Work in progress. These may be papers about completed work that has not yet been published or preliminary results that merit discussion at the conference. Submissions should consist of a title and a short abstract (max. 300 words). Submissions for the non-archival track will undergo a light review process (assessing the relevance of the submission for INLG), and accepted works will be presented as posters. FORMAT Submissions should follow ACL Author Guidelines and policies for submission, review and citation, and be anonymised for double blind reviewing. Please use ACL style files; LaTeX style files and Microsoft Word templates are available at https://acl-org.github.io/ACLPUB/formatting.html. Authors must honor the ethical code set out in the ACL Code of Ethics. If your work raises any ethical issues, you should include an explicit discussion of those issues. This will also be taken into account in the review process. You may find this checklist of use. Authors are strongly encouraged to ensure that their work is reproducible; see, e.g., the following reproducibility checklist. Papers involving any kind of experimental results (human judgments, system outputs, etc) should incorporate a data availability statement into their paper. Authors are asked to indicate whether the data is made publicly available. If the data is not made available, authors should provide a brief explanation why. (E.g. because the data contains proprietary information.) A statement guide is available on the INLG 2026 website. To submit a long or short paper to INLG 2026, authors can either submit directly or commit a paper previously reviewed by ARR. For direct submissions, the deadline for submitting papers is July 15, 2026, 11:59:59 PM (Anywhere on Earth). If committing an ARR paper to INLG, the submission is also made through the INLG 2026 paper submission site, indicating the link of the paper on OpenReview. The deadline for committing an ARR paper to INLG is August 5, 2026, 11:59:59 PM AOE, and the last eligible ARR paper submission deadline for INLG 2026 is May 25, 2026. Demo papers should be submitted directly through the INLG 2026 paper submission site by July 15, 2026, 11:59:59 PM AOE. All accepted papers will be published in the INLG 2026 proceedings and included in the ACL anthology. A paper accepted for presentation at INLG 2026 must not have been presented at any other meeting with publicly available proceedings. Dual submission to other conferences is permitted, provided that authors clearly indicate this in the submission form. If the paper is accepted at both venues, the authors will need to choose which venue to present at, since they can not present the same paper twice. Submitted papers for review at INLG 2026 must not be published elsewhere until after the notification of acceptance. Finally, at least one of the authors of an accepted paper must register to attend the conference. AWARDS INLG 2026 will present several awards to recognize outstanding achievements in the field. These awards are: - Best Long Paper Award: This award will be given to the best long paper submission based on its originality, impact, and contribution to the field of NLG. - Best Short Paper Award: This award will be given to the best short paper submission based on its originality, impact, and contribution to the field of NLG. - Best Demo Paper Award: This award will recognize the best demo paper submitted to the conference. This award considers not only the paper's quality but also the demonstration given at the conference. The demonstration will play a significant role in the judging process. - Best Evaluation Award: The award was introduced at INLG 2024. This award is designed to honour authors who have demonstrated the most comprehensive and insightful analysis in evaluating their results. This award aims to highlight papers where the authors have gone the extra mile in providing a thorough and detailed analysis of their results, offering a nuanced understanding of their findings. COMMUNICATION CHANNELS Website: https://2026.inlgmeeting.org/ Bluesky: https://bsky.app/profile/siggen.bsky.social LinkedIn: https://www.linkedin.com/company/siggen/ Mastodon: https://fediscience.org/@siggen_acl X (formerly Twitter): twitter.com/inlgmeeting —————————————————————————————————————————————————————— Groeten, Emiel van Miltenburg Tilburg University Department of Communication and Cognition (DCC) Tilburg Center for Cognition and Communication (TiCC) Werkdagen: Maandag, Woensdag, Donderdag, Vrijdag. www.emielvanmiltenburg.nl | Github: https://github.com/evanmiltenburg Groeten, Emiel van Miltenburg Tilburg University Department of Communication and Cognition (DCC) Tilburg Center for Cognition and Communication (TiCC) Werkdagen: Maandag, Woensdag, Donderdag, Vrijdag. www.emielvanmiltenburg.nl | Github: https://github.com/evanmiltenburg

1 0

Call for Participation(26/6/2026 online or in person): Workshop on Mechanistic Interpretability and Neuro-symbolic Models by-design
by fabio.massimo.zanzotto＠uniroma2.it 23 Jun '26

23 Jun '26

Site: <https://sites.google.com/view/memo-workshop/> MeMo Workshop https://sites.google.com/view/memo-workshop/ Date: 26/6/2026 Location: online or in person (Rome, Italy) Registration link (free but necessary): <https://forms.office.com/Pages/ResponsePage.aspx?id=Kr7FJGTXxUCZdYLQiuR9Dnl 0_dxZ6e5PtNMq7QTRydxUNkpEODRHQkFVWEhJTDE5S0NCSkdVR0hLQi4u> Register here Are you surprised about the ability of LLMs to perform complex reasoning tasks? Do you have a particular keenness for cracking the code of their inner workings? If the answer is yes, that's the case you are working in mechanistic interpretability or in neuro-symbolic reasoning of LLMs. Then, this is the workshop for you! Observing properties and understanding the inner workings are two sides of the same coin. Another way is possible (e.g., <https://aclanthology.org/2025.findings-acl.785/> Position Paper: MeMo: Towards Language Models with Associative Memory Mechanisms - ACL Anthology)! In the workshop, authors will discuss focused contributions on: * Mechanistic Interpretability by-design * Neuro-symbolic approaches by-design Apologies for multiple posting, but we really hope to see you there.

1 0

Call for Participation: MRL Shared Task at EMNLP 2026
by ljvm2＠cam.ac.uk 22 Jun '26

22 Jun '26

Call for Participation: MRL Shared Task at EMNLP 2026 =========================================== As part of the Multilingual Representation Learning Workshop at EMNLP 2026, we are organizing another collaborative shared task. We are asking contributors to write culturally specific question-answer pairs in their language. All contributors to the dataset will be *invited to be authors on the dataset paper*, which we will submit for publication next year. This is a great project if you’re looking to get involved in NLP research for the first time! We are accepting submissions in any language, but we especially welcome submissions in languages with few speakers and non-standard varieties! Last year, we collectively created a benchmark for over 140 language varieties with over 350 collaborators around the world, called Global PIQA. We are hoping to create another huge dataset with at least as much impact. Help us make sure your language is represented! If you are interested in contributing or getting updates, please fill out the Interest Form: https://docs.google.com/forms/d/e/1FAIpQLSeFeJihiU8UHmb51zuBtLGfa1xq5Lf3tWf… [1] See our task website for up-to-date information: https://mrlbenchmarks.github.io/ [2] And join our Discord to meet potential collaborators! https://discord.com/invite/35tgtC36eT [3] Follow the workshop account on Twitter/X [4] and Bluesky [5] for updates and announcements! Organizing Committee ================== * Catherine Arnett, EleutherAI * Tyler Chang, Google DeepMind * Jesujoba Alabi, Saarland University * Omer Goldman, University of Cambridge * Lj V. Miranda, University of Cambridge * David Stap, NXAI Important Dates ============= * June 8th 2026: Call for participation released, task specifications and submission guidelines published. * July 10th 2026: Information Session, online event to find out how to participate and ask questions. * August 1st 2026: Dataset submission deadline, submit your dataset and dataset description. * September 2026: Decision notification, acceptance decisions sent to participants. * Early October 2026: Benchmark paper publication, organizers work with authors to compile and publish the final dataset and paper. * October 24-29 2026: MRL Workshop @ EMNLP 2026, shared task results presented at the workshop. Important Links ============= [1] https://docs.google.com/forms/d/e/1FAIpQLSeFeJihiU8UHmb51zuBtLGfa1xq5Lf3tWf… [2] https://mrlbenchmarks.github.io/ [3] https://discord.com/invite/35tgtC36eT [4] https://x.com/mrl_workshop [5] https://bsky.app/profile/mrl-workshop.bsky.social

1 0

LxGr2026: Call for Participation - one week to register
by Costas Gabrielatos 22 Jun '26

22 Jun '26

11th Symposium on Corpus Approaches to Lexicogrammar (LxGr2026) LxGr2026 will be held online on Thursday 2 and Friday 3 July 2026. Registration closes in one week (30 June). Programme, abstracts, and registration (free): https://sites.edgehill.ac.uk/lxgr Invited Speakers Stefan Th. Gries<https://www.stgries.info/> (University of California, Santa Barbara, USA) Martin Hilpert<http://members.unine.ch/martin.hilpert> (University of Neuchâtel, Switzerland) Serge Sharoff<https://ssharoff.github.io/> (University of Leeds, UK) If you have problems registering, or have any questions, please contact lxgr(a)edgehill.ac.uk<mailto:lxgr@edgehill.ac.uk>. ________________________________ Edge Hill University<http://ehu.ac.uk/home/emailfooter> Modern University of the Year, The Times and Sunday Times Good University Guide 2022<http://ehu.ac.uk/tef/emailfooter> University of the Year, Educate North 2021/21 ________________________________ This message is private and confidential. If you have received this message in error, please notify the sender and remove it from your system. Any views or opinions presented are solely those of the author and do not necessarily represent those of Edge Hill or associated companies. Edge Hill University may monitor email traffic data and also the content of email for the purposes of security and business communications during staff absence.<http://ehu.ac.uk/itspolicies/emailfooter>

1 0

Model Compression Shared Task @ WMT 2026 - Second (Last) Call for Participation
by Marco Gaido 22 Jun '26

22 Jun '26

Dear all, Apologies for cross-posting. We are pleased to announce the second call of the Model Compression Shared Task <https://www2.statmt.org/wmt26/model-compression.html> at WMT 2026 <https://www2.statmt.org/wmt26/>. This shared task aims to evaluate the potential of model compression techniques in reducing the size of general-purpose large language models, with the goal of achieving an optimal balance between practical deployability and high translation quality in specific machine translation (MT) scenarios. The task’s broader objectives include fostering research into the efficient, accessible, and sustainable deployment of LLMs for MT, establishing a common evaluation framework to monitor progress in model compression across a wide range of languages, and enabling meaningful comparisons with state-of-the-art MT systems through standardized evaluation protocols designed to assess not only translation quality but also computational efficiency. Although the focus is on model compression, the task is closely aligned with the General MT shared task <https://www2.statmt.org/wmt26/translation-task.html>, sharing test data from a subset of its language directions, as well as protocols for automatic MT quality evaluation. Additionally, the task follows the same timeline as the flagship WMT task. We warmly invite participation from academic teams and industry players interested in applying existing compression methods to MT or exploring innovative, cutting-edge approaches. THE TASK IN A NUTSHELL Goal: Reduce the size of a general-purpose LLM while maintaining a balance between model compactness and MT performance. Languages: The second round of the task will focus on a subset of the languages covered by the General MT task, namely: Czech to German, English to Chinese (Simplified), and English to Arabic (Egyptian). Conditions: - Constrained: Participants will compress a specific model, using a predefined pool of data for calibration and fine-tuning (if needed) to ensure directly comparable results. - Unconstrained: Participants are free to compress any model, provided its original size is below 20B parameters, and use any additional data for calibration and fine-tuning. Participation format: Participants will share their compressed models to be run on a standardized hardware environment provided by the organizers. Evaluation Criteria: - Translation quality: Automatically assessed using multiple metrics, e.g. Comet, MetricX, and an LLM-as-a-judge framework. - Model size: Defined by memory usage. - Inference speed: Measured by total processing time over the test set. IMPORTANT DATES - Test data and submission information has just been released - Model Submission deadline: July 2, 2026 - System description paper submission: in line with WMT26 <https://www2.statmt.org/wmt26/index.html> - Camera-ready submission: in line with WMT26 <https://www2.statmt.org/wmt26/index.html> - WMT 2026 Conference (co-located with EMNLP2026 <https://2026.emnlp.org/> in Budapest, Hungary): November, 2026 WEBSITE: https://www2.statmt.org/wmt26/model-compression.html ORGANIZERS: Marco Gaido, Fondazione Bruno Kessler Matteo Negri, Fondazione Bruno Kessler Roman Grundkiewicz - Microsoft Translator TG Gowda - Microsoft Translator CONTACTS: Marco Gaido - mgaido(a)fbk.eu Matteo Negri - negri(a)fbk.eu -- -- Le informazioni contenute nella presente comunicazione sono di natura privata e come tali sono da considerarsi riservate ed indirizzate esclusivamente ai destinatari indicati e per le finalità strettamente legate al relativo contenuto. Se avete ricevuto questo messaggio per errore, vi preghiamo di eliminarlo e di inviare una comunicazione all’indirizzo e-mail del mittente. -- The information transmitted is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. If you received this in error, please contact the sender and delete the material.

1 0

Second CfP and Deadline Extension: 9th Workshop on Natural Language for Artificial Intelligence (NL4AI)
by Elisa Leonardelli 22 Jun '26

22 Jun '26

═══════════════════════════════════════════════════════════ NL4AI 2026 – 9th Workshop on Natural Language for Artificial Intelligence, at the 24th International Conference of the Italian Association for Artificial Intelligence (AIxIA 2026 <https://aixia2026.unipg.it/>) 6–9 October 2026 | Perugia, Italy ═══════════════════════════════════════════════════════════ Website: http://sag.art.uniroma2.it/NL4AI/ Contact Email: nl4ai2026(a)gmail.com ── IMPORTANT DATES ────────────────── [EXTENDED] Paper Submission deadline: 29 June 2026 6 July 2026 🚨 Notification to authors: 31 July 2026 Camera-ready due: 26 August 2026 Workshop Dates: 6–9 October 2026 ──────────────────────────────────── We are pleased to invite submissions to NL4AI 2026, the Ninth Workshop on Natural Language for Artificial Intelligence, to be held in Perugia from the 6th to the 9th of October 2026, within the 24th International Conference of the Italian Association for Artificial Intelligence (AIxIA 2026), and supported by AILC (http://www.ai-lc.it/). The goal of NL4AI is to explore the role of Computational Linguistics and Natural Language Processing in Artificial Intelligence applications. We believe that new technological challenges and opportunities arise at the boundary between NLP and AI. On the one hand, AI applications benefit from a deeper understanding of problems related to Natural Language, and thus the integration of advanced NLP techniques. On the other hand, NLP benefits greatly from being used in wider areas of AI where problems and methodologies related to NL can be evaluated in new contexts. TOPICS OF INTEREST Topics include but are not limited to: - NLP and AI Applications (health, legal domain, social media and journalism, etc.) - Natural Language Interfaces for Human Robot Interaction - Resources, Benchmarks, and Evaluation - Discourse and Pragmatics - Semantics - Natural Language Generation - Creativity, Style, and Narrative Generation - Summarization - Information Extraction in AI Applications - Machine Learning for NLP - LLMs, Foundation Models and Applications - Interpretability, Explainability and Analysis of Models for NLP - Natural Language Inference - Question Answering and Reading Comprehension - Sentiment Analysis, Opinion Mining, and Argumentation - Abusive Language Detection and Analysis - NLP for Fact Checking, Fake News Detection and Analysis - Conversational Agents in Human-Computer Interaction - Speech and Spoken Language Processing - Language and other Multimodality - Multimodal (text-image) data sources - Machine Translation and Multilinguality - Low-Resource NLP and Linguistic Diversity - Cognitive Modeling and Psycholinguistics - Computational Historical Linguistics, Social Science, and Cultural Analytics - Ethics, Fairness, and Societal Impacts of NLP - NLP and Industrial Challenges Accepted papers will be published in the workshop proceedings via CEUR Workshop Proceedings. Depending on the number and quality of papers received, we will consider proposing a special issue in relevant journals. The Program Committee will select the Best Workshop Paper from the accepted papers. SUBMISSIONS We encourage original submissions that describe new theoretical models, applied techniques, and research in progress. Substantial extensions to works already published or presented in other locations are welcome as well. We invite two kinds of submissions: - Short/Demo Paper. Maximum length of 6 pages + up to 2 pages of Acknowledgements/Declaration on Generative AI/References - Regular Papers. Maximum length of 12 pages + up to 2 pages of references Acknowledgements/Declaration on Generative AI/References Please note that papers with less than 25000 characters will be considered short papers in the CEUR proceedings. Submissions Evaluation. Submissions will be peer-reviewed (single-blind) by the program committee members. Evaluation criteria will include novelty, significance for theory/practice, technical soundness, and quality of presentation. Note that reviewers will not be required to evaluate appendices providing a review of the papers. Appendices are intended for including details for reproducibility and/or additional results. How to Submit. Proceedings shall be submitted to CEUR-WS.org for online publication and all papers must follow the 2022 CEUR-ART - 1 Column paper style. The LaTeX template can be downloaded as source file from the NL4AI website <http://sag.art.uniroma2.it/NL4AI/wp-content/uploads/2026/05/CEURART-NL4AI-2…> or accessed as a Template in Overleaf <https://it.overleaf.com/read/cfvwgnqpvpys#a7a014>. All the papers should be submitted via EasyChair: https://easychair.org/conferences/?conf=nl4ai2026 Note: All submissions must be compatible with CEUR (https://ceur-ws.org/) and include the CEUR Declaration on Generative AI section ( https://ceur-ws.org/GenAI/Policy.html). Papers missing this section will be desk rejected. WORKSHOP ORGANIZERS Alessandro Bondielli (University of Pisa) Giovanni Bonetta (Fondazione Bruno Kessler) Elisa Leonardelli (Fondazione Bruno Kessler) Irene Siragusa (University of Palermo) We look forward to seeing you in Perugia! The NL4AI 2026 Workshop Organizers -- -- Le informazioni contenute nella presente comunicazione sono di natura privata e come tali sono da considerarsi riservate ed indirizzate esclusivamente ai destinatari indicati e per le finalità strettamente legate al relativo contenuto. Se avete ricevuto questo messaggio per errore, vi preghiamo di eliminarlo e di inviare una comunicazione all’indirizzo e-mail del mittente. -- The information transmitted is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. If you received this in error, please contact the sender and delete the material.

1 0

37th IEEE International Symposium on Software Reliability Engineering (ISSRE 2026): Last Call for Replications and Negative Results
by Announce 21 Jun '26

21 Jun '26

*** Last Call for Replication and Negative Results *** 37th IEEE International Symposium on Software Reliability Engineering (ISSRE 2026) October 20-23, 2026, 5* St. Raphael Resort and Marina Limassol, Cyprus https://cyprusconferences.org/issre2026/ The Replications and Negative Results (RENE) Track has been introduced in the software engineering community for a while and received overwhelmingly positive feedback. This year, we establish this track at ISSRE and invite researchers to (1) replicate results from previous papers and (2) publish studies with important and relevant negative or null results (results that fail to show an effect, yet demonstrate the research paths that did not pay off). We also encourage the publication of the negative results or replicable aspects of previously published work. For example, authors of a published paper reporting a working solution for a given problem can document in a “negative results paper” other (failed) attempts they made before defining the working solution they published. • Replication studies. The papers in this category must go beyond simply re- implementing an algorithm and/or re-running the artifacts provided by the original paper. Such submissions should at least apply the approach to new data sets (open-source or proprietary). A replication study should clearly report on results that the authors were able to replicate, as well as on the aspects of the work that were not replicable. • Negative results papers. We seek papers that report on negative results. We seek negative results for all types of program comprehension research in any empirical area (qualitative, quantitative, case study, experiment, etc.). For example, did your controlled experiment not show an improvement over the baseline? Even if negative, results obtained are still valuable when they are either not obvious or disprove widely accepted wisdom. Evaluation Criteria Both Replication Studies and Negative Results submissions will be evaluated according to the following standards: • Depth and breadth of the empirical studies • Clarity of writing • Appropriateness of conclusions • Amount of useful, actionable insights • Availability of artifacts • Underlying methodological rigor. A negative result due primarily to misaligned expectations or due to lack of statistical power (small samples) is not a good submission. The negative result should be a result of a lack of effect, not a lack of methodological rigor. Most importantly, we expect replication studies to clearly point out the artifacts upon which the study is built, and to provide the links to all the artifacts in the submission (the only exception will be given to those papers that replicate the results on proprietary datasets that can not be publicly released). Submission Instructions Submissions must be original, in the sense that the findings and writing have not been previously published or under consideration elsewhere. However, as either replication studies or negative results, some overlap with previous work is expected. Please make clear in the paper the overlap with and difference from previous work. All submissions must be in PDF format and conform, at time of submission, to the IEEE Computer Society Format Guidelines: (https://www.ieee.org/conferences/publishing/templates). Authors are strongly encouraged to print the PDF and review it for integrity (fonts, symbols, equations, etc.) before submission, as defective printing can undermine a paper’s chance of success. By submitting to the ISSRE RENE Track, authors acknowledge that they are aware of and agree to be bound by the IEEE Plagiarism FAQ. In particular, papers submitted to the RENE track must not have been published elsewhere and must not be under review or submitted for review elsewhere whilst under consideration for ISSRE 2026. Contravention of this concurrent submission policy will be deemed a serious breach of scientific ethics, and appropriate action will be taken in all such cases. To check for double submission and plagiarism issues, the chairs reserve the right to (1) share the list of submissions with the PC Chairs of other conferences with overlapping review periods and (2) use external plagiarism detection software, under contract to the IEEE, to detect violations of these policies. Submissions to the RENE Track can be made via the ISSRE RENE track submission site： https://easychair.org/conferences?conf=issre2026 . Submission Length: The ISSRE RENE Track accepts submissions of two lengths: (1) New replication studies and new descriptions of negative results should have a length of up to 10 pages, plus 2 pages which may only contain references. (2) Negative results documented during the preparation of previously published work by the authors should be described in up to 5 pages, plus 1 page, which may only contain references (e.g., as previously mentioned, authors of a published paper can document negative results they obtained while working on it, such as methodologically sound solutions that did not work). Important note 1: Both types of papers (replication and negative results) will be included as part of the main conference proceedings. Important note 2: The RENE track does not follow a double-anonymous review process. Publication and Presentation Upon notification of acceptance, all authors of accepted papers will receive further instructions for preparing the camera-ready versions of their submissions. If a submission is accepted, at least one author of the paper is required to have a full registration for ISSRE 2026, attend the conference, and present the paper in person. All accepted papers will be published in the conference electronic proceedings. The presentation is expected to be delivered in person, unless this is impossible due to travel limitations (e.g., related to health or visa). Details about the presentations will follow the notifications. The official publication date is the date the proceedings are made available in the IEEE Digital Libraries. The official publication date affects the deadline for any patent filings related to published work. Purchases of additional pages in the proceedings are not allowed. Important Dates (AoE) • Submission deadline: July 5, 2026 • Notification of acceptance: August 12, 2026 • Camera-ready copy submission: August 19, 2026 • Author registration deadline: August 19, 2026 Organisation General Chairs • Leonardo Mariani, University of Milano - Bicocca, Italy • George A. Papadopoulos, University of Cyprus, Cyprus Program Coordinator • Roberto Natella, GSSI, Italy Research Program Committee Chairs • Domenico Cotroneo, UNC Charlotte, USA • Jie M. Zhang, King's College London, UK Industry Program Chairs • Jinyang Liu, Bytedance, USA • Sigrid Eldh, Ericsson AB, Sweden Workshop Chairs • Georgia Kapitsaki, University of Cyprus, Cyprus • August Shi, The University of Texas at Austin, USA Doctoral Symposium Chairs • Stefan Winter, LMU Munich, Germany • Lili Wei, McGill University, Canada Fast Abstract Chairs • Luigi Lavazza, University of Insubria, Italy • Yintong Huo, SMU, Singapore JIC2 Chair • Helene Waeselynck, LAAS-CNRS, France Publicity Chairs • Allison K. Sulivan, The University of Texas at Arlington, USA • Jose D'Abruzzo Pereira, University of Coimbra, Portugal Publication Chairs • Sherlock Licorish, Otago Business School, New Zealand • Maria Teresa Rossi, GSSI, Italy Artifact Evaluation Chairs • Naghmeh Ivaki, University of Coimbra, Portugal • Fumio Machida, University of Tsukuba, Japan Diversity and Inclusion Chair • Eleni Constantinou, University of Cyprus, Cyprus Financial Chair • Costas Pattichis, University of Cyprus, Cyprus Web Chairs • Michalis Ioannides, Easy Conferences LTD • Elena Masserini, University of Milano - Bicocca, Italy Registration Chair • Easy Conferences LTD

1 0

[ÚLTIMA CHAMADA] XVII Encontro de Linguística de Corpus (ELC) e XIV Escola Brasileira de Linguística Computacional (EBRALC)
by Jackson Souza 19 Jun '26

19 Jun '26

*XVII Encontro de Linguística de Corpus (ELC)* *XIV Escola Brasileira de Linguística Computacional (EBRALC)* *9 a 12 de novembro de 2026, na Universidade Federal da Bahia* *ÚLTIMA CHAMADA* para ELC/EBRALC 2026, um dos principais encontros acadêmicos dedicados às relações entre linguagem, tecnologia e sociedade. Nesta edição, o evento trará como tema central: *“Linguística de Corpus, Inteligência Artificial e Transformação Digital: Dados, Métodos e Impactos Sociais na Era Digital”.* O evento [presencial] reunirá pesquisadores, estudantes e profissionais interessados em discutir os desafios e as oportunidades das tecnologias linguísticas contemporâneas, com foco em inteligência artificial, ética de dados e análise baseada em grandes volumes de informação. O *ELC* consolida-se como um espaço de divulgação científica e debate acadêmico, promovendo o intercâmbio de pesquisas sobre linguagem em contextos digitais e sociais. Já a *EBRALC* possui caráter formativo, oferecendo oficinas e minicursos voltados à aplicação prática de ferramentas de Linguística de Corpus e Processamento de Linguagem Natural. Nesta edição, o encontro será realizado na *Universidade Federal da Bahia (UFBA)*, fortalecendo a presença da pesquisa linguística baseada em dados na região Nordeste e incentivando o diálogo interdisciplinar. Compartilhem a chamada em suas respectivas instituições e programas de pós-graduação! *Indicações de temas* ● Linguística de corpus e análise baseada em dados ● Processamento de Linguagem Natural ● Modelos de linguagem e representação semântica ● Métodos computacionais e análise de dados linguísticos ● Linguagem, discurso e cultura digital ● Ética, governança e impactos sociais da IA ● Linguística de corpus aplicada ● Terminologia, Lexicografia ● Tradução ● Linguística de corpus e ensino ● Linguística de corpus e cultura digital *Datas importantes* *28/06/2026* – Submissão de trabalhos para ELC *28/06/2026* – Submissão de propostas de oficinas/minicursos para EBRALC *27/07/2026* – Resposta aos autores/proponentes *09/08/2026* – Envio das versões finais 09 a 12/11/2026 – Realização do evento *Submissão de propostas* Acesse o formulário: https://forms.gle/d8uHzNY86xWSh7YSA *Dúvidas e contato* Site do evento <https://sites.google.com/view/elc-ebralc2026/in%C3%ADcio>. elcebralc2026(a)gmail.com | acksoncruz(a)ufba.br <jacksoncruz(a)ufba.br> --

1 0

Two PhD positions in Uncertainty Quantification and Communication for LLMs
by Christian Hardmeier 19 Jun '26

19 Jun '26

We have two open PhD positions in our project on Uncertainty Quantification and Communication for Large Language Models. Large language models (LLMs) have become immensely popular tools for laypeople and experts to find quick answers to any questions, including such that require specialized knowledge or complex reasoning. Their replies are far from always correct. Right or wrong, but often couched in a confident and persuasive tone, they may fool even experts into believing entirely false statements. Accurate and trustworthy LLM tools must know how much confidence a model has in its output and communicate this to the user in a nuanced and understandable form, respecting the principles of communication between humans. Our interdisciplinary project unites machine learning, natural language processing and linguistics. We study how LLMs acquire and verbally communicate (un)certainty, develop novel methods in Bayesian uncertainty quantification and apply them to LLMs in health applications. Using methods from linguistics, we emphasize targeted communication that gets interpreted correctly by diverse users, including laypeople and experts, and create LLMs that communicate their uncertainty according to humanlike standards. One position is in natural language processing at the IT University of Copenhagen, supervised by me and Jes Frellsen (DTU). In this position, you will develop methods to help LLMs express their uncertainty in a way that humans understand, while matching the perceived uncertainty to the model's internal state. Application deadline 24 June (very soon!). This position was advertised before. Apply here: https://candidate.hr-manager.net/ApplicationInit.aspx?cid=119&ProjectId=181… The second position is in machine learning at the Technical University of Denmark, supervised by Jes Frellsen and me. In this position, you will develop efficient machine learning methods to quantify the uncertainty of large language models. This position is new. Application deadline 7 August. Apply here: https://efzu.fa.em2.oraclecloud.com/hcmUI/CandidateExperience/da/sites/CX_2… Both positions include an extended research stay at the University of Edinburgh, the first with Prof. Hannah Rohde (Linguistics) and the second with Prof. Ivan Titov (NLP/machine learning). -- Christian Hardmeier Associate Professor, IT University of Copenhagen https://christianhardmeier.rax.ch/

1 0

2026

2025

2024

2023

2022