Improving Language Models through Learning from Dialogue Interaction
Co-located with EMNLP 2026 — 28 October 2026, Budapest
Website: https://lm-playschool.github.io/
Starter Kit: https://github.com/lm-playpen/playpen
The submission deadlines for the LM Playschool Workshop are almost here! The challenge submission deadline is this Sunday, July 5, 2026 (only 2 days away!), followed shortly by the direct paper submission deadline on July 12, 2026 (9 days away!).
📝 SUBMISSION TRACKS
We welcome either long or short submissions for the following tracks:
1. Challenge track: Technical reports for the LM-Playschool challenge (archival).
2. Paper-only track: Work-in-progress (archival or non-archival) or recently published papers (non-archival).
🏆 CHALLENGE TRACK (SHARED TASK)
The shared task focuses on post-training LLMs to master communicative skills in unseen dialogue games while retaining original language capabilities. Participants are free to choose any base model; evaluation is based on improvement relative to that base model on an unseen test set.
Not signed up yet? Register here: https://forms.gle/fhpXPH5kZk4psPXp9
🛠️ STARTER KIT
Our sandbox environment Playpen is available on GitHub and ready to use. Key features:
* Comprehensive Evaluation: A single command to get your "clemscore" (interactive competence) and "statscore" (classic benchmarks).
* Training Recipes: Example scripts for SFT and GRPO to help models learn from game-state success.
* Resource Friendly: We encourage using the Qwen3.5 family (0.8B to 27B) to ensure participation is possible with modest compute.
🎯 PAPER-ONLY TRACK: TOPICS OF INTEREST
We welcome original research and work-in-progress on:
* Architectures and training regimes for interactive agents.
* Intrinsic rewards and learning signals (RL from game-state success).
* Benchmarking via dialogue games.
* Data efficiency and social interaction.
* Social cognition and Theory of Mind in interactive systems.
* Human-agent collaboration and coordination.
* Embodied interactive agents.
* Communicative and perceptual grounding.
📅 IMPORTANT DATES
* Challenge submission deadline: July 5, 2026 (only 2 days away!)
* Direct paper submission deadline: July 12, 2026 (9 days away!)
* Pre-reviewed ARR commitment deadline: August 2, 2026
* Notification of acceptance: August 8, 2026
* Camera ready due: August 23, 2026
* Challenge winners announced: Early October 2026
* Workshop at EMNLP 2026: October 28, 2026 — Budapest
For more information, visit our website: https://lm-playschool.github.io/
We look forward to your submissions!
The LMP 2026 Organizing Committee:
Raffaella Bernardi, Raquel Fernández, Mario Giulianelli, Sherzod Hakimov, Alexander Koller, Dieu-Thu Le, Oliver Lemon, Davide Mazzaccara, Sabrina McCallum, David Schlangen, Alessandro Suglia
Dear all,
Please see the information on job opportunities below.
I’d be grateful if you could share with potential candidates.
Where:
The Text & Language Lab in the Department of Digital Humanities and Social Studies (DHSS) at Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) is recruiting up to five outstanding postdoctoral and doctoral researchers. Join a highly collaborative team pursuing an ambitious research agenda on various aspects of language in today’s digital world. Led by Alexander von Humboldt-Professor Michaela Mahlberg, the lab offers an inspiring environment where curious researchers work across disciplines and produce results with clear, real-world relevance.
What:
Depending on your qualifications and experience there are different options of appointment, which include opportunities to make a contribution to the teaching of the Department.
• PhD positions are for up to 4 years (75% or 100%), initial contract 1 year with extension after successful completion of first year
• Postdoctoral positions for up to 4.5 years (100 %), initial contract 2 years, after successful completion of that period there is the opportunity to extend the positions until 31.03.2031
The positions:
1) Postdoctoral researcher with focus on web application development and CLiC (clic-fiction.com)
Specific responsibilities will include:
• Corpus compilation
• Modular software development
• Leading on the organisation of training workshops and dissemination activities
• Developing training materials for workshops
• Producing documentation
• Collaboration with external software developers
• Working as part of a team, with the responsibility to manage specific work packages and lead clear sub-projects (including publications and grant application development)
• Managing project tasks such as supervising student assistants and providing progress reports
2) Postdoctoral researcher with focus on experimental methods
Specific responsibilities will include:
• Designing and running experiments that focus on the engagement with texts and tools (reader response, surveys, interviews, eye-tracking, Human-AI interaction)
• Analysing research data
• Leading on the organisation of training workshops and dissemination activities
• Working as part of a team, with the responsibility to manage specific work packages and lead clear sub-projects (including publications and grant application development)
• Managing project tasks such as supervising student assistants and providing progress reports
3) Doctoral researcher - PhD Project: Fictional people and the climate crisis
The project will be situated within a research context that deals with textual patterns of characterization with a focus on the relationship between fictional people and their environment. This environment will cover both the natural and the built environment. The textual patterns will be studied on the basis of data from a variety of texts (including climate and science fiction). Methods of analysis will draw on computational textual analysis. The specific research questions of the project will be developed together with the successful candidate.
Specific responsibilities will include:
• Text and data analysis
• Corpus design and compilation
• Working as part of a team, with the responsibility to manage specific work packages and lead clear sub-projects (including publications and grant application development)
• Managing project tasks such as supervising student assistants and providing progress reports
More detail on required qualifications and how to apply:
https://www.fau-jobs.de/jobposting/621d437fb9ed15d519420c8046d50aa9431c66ec0
Deadline: 24 July 2026
If you have any questions don’t hesitate to contact me
Michaela
--
Professor Michaela Mahlberg
https://michaelamahlberg.com/<https://linkprotect.cudasvc.com/url?a=https%3a%2f%2fmichaelamahlberg.com%2f…>
Alexander-von-Humboldt Professor & Professor of Digital Humanities<https://www.youtube.com/watch?v=bgkKhcwvWgI>
Head of Department of Digital Humanities and Social Studies (DHSS)<https://linkprotect.cudasvc.com/url?a=https%3a%2f%2fwww.dhss.phil.fau.de%2f…>
FAU - Friedrich-Alexander-Universität Erlangen-Nürnberg<https://linkprotect.cudasvc.com/url?a=https%3a%2f%2fwww.fau.de%2f&c=E,1,fU0…>
Honorary Professor of Corpus Linguistics University of Birmingham, UK<https://www.birmingham.ac.uk/>
Editor of the International Journal of Corpus Linguistics <https://linkprotect.cudasvc.com/url?a=https%3a%2f%2fbenjamins.com%2fcatalog…>
President of the Dickens Society<https://dickenssociety.org/>
Host of the Life and Language Podcast <https://podcasters.spotify.com/pod/show/michaela-mahlberg/>
https://www.linkedin.com/in/michaela-mahlberg/
=========================================================
2nd Call for Papers - Deadline EXTENDED: HeMAI 2026
Multimodal Interaction with Generative AI Health Applications
Workshop at ICMI 2026, Naples, Italy, 9 October 2026 (in person)
https://qulab.github.io/HeMAI2026/
Submission via PCS until July 13, 2026
=========================================================
Generative AI is changing how people interact with health technology. Large language models, multimodal foundation models, and conversational agents make it possible to combine text, speech, vision, and physiological signals in ways that weren't practical a few years ago, and they raise difficult questions about usability, safety, explainability, trust, and evaluation when the stakes involve someone's health.
HeMAI 2026 brings HCI, AI, and health researchers together to work through those questions. We welcome contributions on multimodal interaction techniques for health systems, conversational and embodied agents in healthcare, integration of text/speech/vision/biosignals, explainability and transparency, human-AI collaboration, safety and trust, ethical and regulatory issues, evaluation methodologies, and real-world deployments.
Submission types:
- Full research papers (up to 8 pages, excluding references)
- Short / work-in-progress / position / demo papers (up to 4 pages, excluding references)
Submissions follow ICMI 2026 author guidelines: https://icmi.acm.org/2026/guidelines/
Papers rejected from the main ICMI track are welcome if they fit the scope.
Important dates (AoE):
- Paper submission: 6 July 2026 (via PCS)
- Notification: 29 July 2026
- Camera-ready: 1 August 2026
- Workshop: 9 October 2026
Accepted papers will appear in the workshop proceedings associated with ICMI 2026.
Organizers:
- Stefan Hillmann (TU Berlin)
- Sebastian Möller (TU Berlin & DFKI Berlin)
- Catherine Pelachaud (CNRS--ISIR, Sorbonne University)
- Lisa Raithel (TU Berlin & BIFOLD & DFKI Berlin & Charité--IKIM)
- Roland Roller (DFKI Berlin)
Workshop website: https://qulab.github.io/HeMAI2026/
We are looking forward to your submissions!
We are recruiting a Doctoral Researcher and a Postdoctoral Researcher! Both roles focused on training health foundation models and medical reasoning using Finland's nationwide health databases.
💻 Access to world-class computing resources, including local clusters (Roihu and Triton) and the LUMI Supercomputer (one of the world's fastest and greenest).
🤝 Direct integration into the ELLIS Institute Finland and the University of Turku research ecosystems.
🌲 Excellent work-life balance and competitive salary in Finland.
📅 Application Deadline: August 17, 2026 at 16:00 (Helsinki time)
Find full job details and apply here:
https://www.olaresearch.org/news/job-openings-foundation-health-models.html
Dear Colleagues,
We are pleased to invite submissions to the Special Issue "Big Data
Analytics and Mining for Information Retrieval" in the "Big Data and
Cognitive Computing" Journal (IF 5.3, CiteScore 11.4).
This Special Issue seeks advanced analytics and mining methods that
integrate big-data technologies with intelligent retrieval models. We
welcome original research articles and review papers on research areas
including, but not limited to:
- web search
- social media analytics
- recommendation systems
- enterprise search
- digital libraries
- biomedical informatics
For details and submission instructions, visit the Special Issue
webpage:
https://www.mdpi.com/journal/BDCC/special_issues/4643ZF82B5
If you are interested in submitting a manuscript, kindly register a
tentative title and abstract via the "Submit Abstract to Special Issue"
form on the Special Issue webpage at your earliest convenience.
Please feel free to share this invitation with colleagues and
collaborators.
We look forward to receiving your contributions.
Kind regards,
Guest Editor
Dr. Ida Mele
IASI-CNR, Rome, Italy
CALL FOR PAPERS
The 30th Annual Conference of the Foundation for Endangered Languages,
FEL XXX (2026)
"Endangered Languages and Innovative Technologies: Documentation,
Processing and Revitalisation"
Organised by the Foundation for Endangered Languages(FEL
<https://ogmios.org/>),
the Centre d'Études en Sciences Sociales sur les Mondes Africains
Américains et Asiatiques (CESSMA <https://www.inalco.fr/en/cessma>)
and the Institut National des Langues et Civilisations Orientales
(INALCO <https://www.inalco.fr/en>)
Paris, France, 3-5 November 2026
The conference aims to create a space for dialogue between researchers,
technologists, and, crucially, language communities themselves,
concerning the opportunities and challenges presented by innovative
technologies in efforts to prevent language loss and promote the
maintenance and revitalisation of endangered languages. We strongly
encourage submissions from community members, educators, activists, and
practitioners, as well as presentations of collaborative work between
academic and non-academic partners.
More about the theme: https://www.ogmios.org/conferences/2026/theme.php
Important dates:
# 10July2026:Deadlineforsubmission of abstracts
NB:***Due to the tight schedule this deadline can not be extended!*
# 13 July 2026: Registration opens
# 01 August2026:Selectedapplicantsinformed
# 15 September2026:Deadlineforsubmission of extended versions of accepted
abstracts
# 03-05November 2026:Conference dates
# 06 November 2026: Excursion (to be confirmed)
Conference website: https://ogmios.org/conferences/2026
Email: fel2026(a)ogmios.org
--
------------------------------------------------------------------------
Steven Krauwer, CLARIN/FEL/ELSNET/TLC, Drift 10, 3512 BS Utrecht, NL
Dear Corpora-list community,
We are excited to welcome you to the 9th Workshop on Event Extraction and Understanding: Challenges and Applications (EEUCA 2026), taking place July 3, 2026, as part of ACL 2026!
This year's workshop highlights how our field continues to evolve from traditional event extraction toward large language models, multimodal event understanding, symbolic reasoning, agent-based systems, and socially impactful AI applications. Some of the key themes of EEUCA 2026 include:
* Event extraction and understanding with LLMs
* Multimodal analysis of real-world events
* Low-resource and multilingual approaches
* Benchmark creation and evaluation
* Geopolitical event analysis
* Shared tasks on multimodal vaccine discourse and toxicity detection in online gaming communities
If you are attending ACL 2026, we warmly invite you to join us on July 3. Whether your interests are in information extraction, NLP, computational social science, multimodal AI, or generative models, we would love to see you there!
Proceedings: https://aclanthology.org/events/acl-2026/#2026eeuca-1
🗓️ Workshop schedule and additional information:
https://research.ku.edu.tr/research-infrastructure/research-centers-and-uni…
We sincere thank to all authors, shared task participants, reviewers, program committee members, keynote speakers, and organizers whose hard work made this year's workshop possible. We look forward to welcoming the community and discussing the next generation of event-centered AI research.
Ali Hürriyetoğlu, Hristo Tanev, Surendrabikram Thapa
[Apologies for Cross Posting]
═══════════════════════════════════════════════════════════
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, 23:59 AoE🚨
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.
Dear colleagues,
The submission deadline for the 6th Workshop on Computational Perspectives on Social Science (CPSS 2026), co-located with KONVENS 2026 in Hamburg, has been extended to ***July 10, 2026 (AoE)***.
CPSS brings together researchers from NLP, Computational Linguistics, Computational Social Science, and Computational Political Science to foster interdisciplinary exchange on computational approaches to studying social and political phenomena.
This year’s special theme is:
Can (and should) LLMs simulate human perspectives?
We especially invite submissions on the simulation of human perspectives with LLMs, including questions related to ethics, bias, data quality, evaluation, and reproducibility. We also welcome contributions on the broader spectrum of Computational Social Science and NLP, including topics such as language model bias, modeling complex social concepts, political communication, synthetic and human data quality, data leakage, open science, and interdisciplinary methodologies.
We invite three submission types:
* Archival papers (long and short papers, also via ARR)
* Non-archival abstracts (1 page) describing ongoing or previously published work
* PhD Forum submissions (2 page abstracts) for doctoral researchers at all stages
Important dates
* Direct submissions (archival and non-archival): July 10, 2026 (AoE)
* ARR submissions (archival only): July 15, 2026
* Notification of acceptance: August 7, 2026
For the full Call for Papers and submission details, please visit:
https://sites.google.com/view/cpss2026konvens/home-page
We look forward to your submissions and hope to welcome you to Hamburg this September!
Best regards,
The CPSS 2026 Organizing Committee
***ENGLISH VERSION BELOW***
PRAZO DE CANDIDATURA: 7 DE JULHO DE 2026
Estão abertas as candidaturas ao Curso de Especialização em Linguística Forense da Universidade do Porto (7ª edição).
Este curso, o primeiro curso de pós-graduação de 60 ECTS no espaço de língua portuguesa dedicado à linguística forense, reflete o papel pioneiro da Universidade do Porto no desenvolvimento de formação académica especializada nesta área. O curso, concebido em modo b-learning para proporcionar preparação avançada na interseção entre linguagem, direito e justiça, oferece um currículo rigoroso, inovador e altamente relevante para graduados e profissionais que desejam aprofundar a sua especialização em linguística forense.
Através de uma combinação de fundamentos teóricos e aplicações práticas, o curso visa reforçar a competência analítica e apoiar o desenvolvimento profissional em áreas de crescente relevância social e institucional. Esta formação constitui uma oportunidade distinta para aqueles que desejam envolver-se com uma das áreas mais dinâmicas e especializadas do estudo da linguagem.
Enquanto universidade pública, a Universidade do Porto oferece este programa a um nível de propinas comparativamente acessível, tornando a educação especializada de elevada qualidade mais acessível a um leque mais amplo de pessoas candidatas.
As candidaturas estão abertas até 7 de julho de 2026.
Para mais informações, não hesite em entrar em contacto, ou visite https://sigarra.up.pt/flup/pt/cur_geral.cur_view?pv_curso_id=13881
***ENGLISH VERSION***
APPLICATION DEADLINE: 7 JULY 2027
We are pleased to announce that applications are now open for the Specialisation Course in Forensic Linguistics at the University of Porto (the 7th cohort of the programme).
This programme, the first 60 ECTS-credit postgraduate course in the Portuguese-speaking arena dedicated to forensic linguistics, reflects the University of Porto's pioneering role in the development of specialised academic training in this field. The course, which was designed to provide advanced preparation at the intersection of language, law, and justice, offers a rigorous, innovative and highly relevant curriculum for graduates and professionals seeking to further their expertise in forensic linguistics.
Through a combination of theoretical foundations and practical applications, the course aims to strengthen analytical competence and support professional development in areas of growing social and institutional relevance. It stands as a distinctive opportunity for those who wish to engage with one of the most dynamic and specialised areas of linguistic study.
As a public university, the University of Porto is able to offer this programme at a comparatively accessible tuition level, making high-quality specialised education more attainable for a broader range of candidates.
Applications are open until 7 July 2026.
Please do not hesitate to reach our to us for further information - or visit https://sigarra.up.pt/flup/pt/cur_geral.cur_view?pv_curso_id=13881
All best
Rui
Rui Sousa Silva
Professor Auxiliar / Assistant Professor
NORTE IA+ | Principal Investigator
Faculdade de Letras, Universidade do Porto | Faculty of Arts and Humanities, University of Porto
www.linguisticaforense.pt<http://www.linguisticaforense.pt/> | https://s.up.pt/qjur | http://tinyurl.com/37w2ec6x | norteia.pt<http://www.norteia.pt/>
Publicação mais recente / Latest publication: “The facts speak for themselves”: dismantling conspiracy theories as disinformation<https://www.degruyterbrill.com/document/doi/10.1515/lingvan-2024-0160/html>
Escola Prática, Curso de Especialização em Linguística Forense<https://sigarra.up.pt/flup/pt/cur_geral.cur_view?pv_curso_id=13881>
Selo INOVPED - Inovação Educativa 2025
NORTE2030-FEDER-02724200 | NORTE 2030 - Programa Operacional Regional do Norte (NORTE 2030 - Projetos Integrados ICDT), Portugal 2030 e Comissão Europeia.Comissão de Coordenação e Desenvolvimento Regional do Norte - www.norteia.pt<http://www.norteia.pt/>
AVISO DE CONFIDENCIALIDADE: Esta mensagem e os seus anexos são confidenciais e dirigidos unicamente aos destinatários da mesma. Se não for o destinatário, solicito que não faça qualquer uso do seu conteúdo e proceda à sua eliminação, notificando-me do sucedido. Obrigado.
//
CONFIDENTIALITY WARNING: This message and its attachments are confidential and exclusively addressed to the recipients above. Should you not be one of the recipients, I kindly ask you not to make use of its contents and delete the message and its attachments. Please reply to this e-mail to warn me about this incident. Thank you.