LLM4Good26 - CfP – CDL-RecSys

Call for Papers

Large Language Models (LLMs) are transforming personalized services by enabling adaptive, context-aware recommendations and interactions. However, deploying these models at scale raises significant concerns about environmental impact, fairness, privacy, and trustworthiness, including high energy consumption, biased outputs, privacy breaches, and hallucinations.

LLM4Good is a half-day workshop dedicated to addressing these challenges by fostering dialogue on sustainable and ethical approaches to LLM-based personalization. The workshop brings together researchers and practitioners to discuss energy-efficient techniques, bias mitigation, privacy-preserving methods, and responsible deployment strategies. It also provides a forum for examining broader meta topics, including sustainable LLM design, trustworthy personalization approaches, innovative generative and conversational applications, novel evaluation methodologies, and the societal impact of these technologies. In alignment with the Sustainable Development Goals and Digital Humanism principles, LLM4Good aims to advance the development of trustworthy, human-centric LLM systems that can positively influence education, healthcare, and other key domains.

Topics of Interest

We invite contributions that focus on, but are not limited to, the following areas:

Generative and Conversational LLM Applications
- Personalized conversation agents, chatbots, and question-answering systems.
- LLM-driven content creation or item generation (e.g., text-based or multimodal).
- Integration of knowledge graphs, domain experts, and hybrid architectures.
- Potential for personalization in education, healthcare, or tourism.
Sustainable LLMs
- Techniques for model compression, pruning, or energy-efficient inference.
- Life cycle assessment of LLM deployments (computational costs, carbon footprints).
- Sharing and reusing pre-trained models to reduce resource duplication.
Trustworthy LLM-based Personalization
- Bias detection and mitigation (e.g., fairness for underrepresented groups).
- Ethical frameworks and regulatory compliance (e.g., GDPR, AI Act).
- Privacy-preserving personalization (federated learning, differential privacy).
- Strategies to combat hallucinations and misinformation in generative recommendations.
LLM-based Agents and Multi-Agent Systems
- Autonomous and semi-autonomous LLM agents for personalized assistance and decision support.
- Safety mechanisms, oversight, and failure recovery in autonomous LLM agents.
- Agent-based personalization in complex domains (e.g., education, healthcare, smart cities).
- Resource-aware and sustainable agent orchestration (e.g., cost-aware planning, adaptive model selection).
Evaluation and Benchmarking
- Novel metrics for evaluating sustainability, fairness, and explainability.
- Benchmarks and datasets for robust testing of LLM-based personalized systems.
- User studies, real-world deployments, and reliability under adversarial conditions.
- LLMs and agent-based systems as evaluators for automated and scalable assessment.
Societal Impact and Digital Humanism
- Developing strategies for LLM-based personalization that respect human values, inclusivity, and cultural diversity while addressing socio-cultural impacts.
- Governance models, policies, and guidelines for safe and transparent AI use.
- Impact on democracy, labor markets, education, and local communities.

Important Dates

~~April 9, 2026~~ April 15, 2026 Submission Deadline
April 28, 2026 Notification
May 7, 2026 Camera-ready Deadline

Please note: All deadlines refer to 11:59 pm AoE (Anywhere on Earth) time.

Workshop Format

The workshop will be held as a half-day workshop at ACM UMAP 2026 in Gothenburg.

Submission Guidelines

All submissions must be written in English. Papers should be submitted electronically in PDF format through the EasyChair submission system at https://easychair.org/conferences/?conf=llm4good.

Format

Long papers: 10 or more (max. 12) standard pages, including references.
Short papers: 5–9 standard pages, including references.
Position/Poster papers: less than 5 standard pages, including references. Such papers are not regarded as citable contributions and should be handled like an abstract. Poster papers that contain novel results (and are not summarizing results already published elsewhere) may be an exception. It depends on the substance of the content of the paper.

Anonymity

The peer review process is single-blind.

Templates

All papers must use the CEUR-WS template in one-column format.

Official templates:

o Offline version: http://ceur-ws.org/Vol-XXX/CEURART.zip

o Overleaf version: https://www.overleaf.com/latex/templates/template-for-submissions-to-ceur-workshop-proceedings-ceur-ws-dot-org/wqyfdgftmcfw

LaTeX is strongly preferred.

If LaTeX is not used, authors must strictly follow the ODT template instructions:

o The ODT template is provided within the CEURART package.

o Microsoft Word must not be used for the ODT template.

o The Libertinus font family is mandatory; installation instructions are included in the template.Papers that do not comply with these requirements will not be suitable for publication in CEUR-WS.

Publication

Each accepted workshop paper must be accompanied by a distinct full author registration, completed by the early registration date cut-oﬀ. Each accepted workshop paper can be presented either in person or online and all workshop papers will be published in a single CEUR-WS proceedings volume.

License:
Each paper must include a CC BY 4.0 license footnote on the first page, with the following text: “Copyright © JJJJ for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).” where JJJJ must be replaced by the publication year.

Declaration of Generative AI:
Each paper must include a mandatory Declaration of Generative AI, in accordance with:
https://ceur-ws.org/GenAI/Policy.html

Event information:
Each paper must include the following information on the first page. Please, carefully complete this part in the template:

%% This command is for the conference information

\conference{}

by adding

“Joint Proceedings of the ACM UMAP Workshops 2026, UMAP 2026, June

8–11, 2026, Gothenburg, Sweden”

Author Agreement:

CEUR-WS requires a signed AUTHOR AGREEMENT from the contact author of each paper.

You can find the template here: https://drive.google.com/drive/folders/1ywmBv-r-CIm-Bu-9uuintU2TUCqg8f92?usp=sharing