Apologies for cross-posting
------------------------------------------------------
Dear colleagues,
We invite you to submit to the special session on “Emergent
Phenomena in Deep Representations and Large Language Models” as a
part of IJCNN 2024 and IEEE WCCI 2024, which will be located in
Yokohama, Japan.
We are looking forward to your contributions.
Please find the CfP below.
Best wishes,
On behalf of Organising Committee
Özge Alacam
------------------------------------------------------
First Call for Papers: Special Session on Emergent Phenomena in Deep
Representations and Large Language Models @IJCNN 2024 & IEEE
WCCI 2024:
Deep learning models trained on large datasets have shown
spectacular performance in a wide range of tasks demonstrated by
current applications of Large Language Models. However, recent works
have shown that the abilities large machine learning models acquire
often emerge unpredictably with increasing model complexity or
training dataset size. These emergent phenomena include the
unexpected appearance of abilities for which the model was not
explicitly trained, but they might also be related to unexpected
performance boosts due to the increased model complexity. Emergent
phenomena are not always beneficial: larger models may pick up new
biases from the training data or start hallucinating.
To move towards increasingly sustainable, reliable, and explainable
applications of AI systems, it is necessary to increase the
understanding of the mechanisms surrounding emergent phenomena.
Moreover, this effort provides increased insight into the learning
process behind the acquisition of abilities of large models to
perform specific tasks. Important research questions relate to the
definition of emergent phenomena, their causes (what controls which
abilities are acquired and when?), training efficiency, and training
data quality (e.g., acquiring desired abilities with less
computational effort), prompting strategies to get or test for
desired model behaviour (e.g., a chain of thought), and further
verification methods of model abilities and properties.
The primary goal of this special session is (i) to discuss the
emergent abilities and risks in deep neural networks and
representations from very different angles and (ii) facilitate
networking and encourage collaboration between various research
fields that approach this issue from different perspectives, like
computational linguistics, ethics in AI, computer science, physics,
etc.
Topics of interest include, but are not limited to:
• The definition of emergence in the context of NLP and ML
• Prompting strategies
• Physics-based/inspired analyses (e.g. phase transitions in
ML models)
• Explainability and interpretability (XAI)
• Evaluation measures for model ability, monitoring
strategies, assessment of model abilities (e.g. technical or
psychology-based)
• Knowledge distillation, model pruning, energy-efficient
models.
• Mitigation strategies for emergent risks and model
deterioration.
• Fine-tuning and Retrieval-augmented generation (RAG)
• Papers focusing on specific emergent phenomena (reasoning,
creativity, double descent phenomena etc.)
The website for the call for papers is accessible at https://sites.google.com/view/emergenn/call-for-papers
Organising Committee:
------------------------------
• Dr. Özge Alacam (Ludwig-Maximilian University & Uni
Bielefeld, Germany)
• Dr. Michiel Straat (Uni Bielefeld, Germany)
• Prof. Dr. Hinrich Schütze (Ludwig-Maximilian University,
Germany)
• Prof. Dr. Alessandro Sperduti (University of Padova, Italy)
Important Dates:
------------------------------
• January 15, 2024 - Paper Submission Deadline
• March 15, 2024 - Notification of Acceptance
• May 1, 2024 - Camera-ready Deadline &
Early Registration Deadline
• June 30 - July 5, 2024 - Main Conference (IEEE WCCI 2024,
Yokohama, Japan)
* All deadlines are 11:59 PM UTC-12:00 ("anywhere on Earth")
Submission Format and Platform:
------------------------------
• Submissions will be through the IEEE
WCCI 2024 Submission page.
• Each paper is limited to 8 pages, including figures,
tables, and references. Please refer to the author guidelines
provided by IEEE WCCI 2024
• Please specify during the submission that your paper is
intended for the Special Session: Emergent Phenomena in Deep
Representations and Large Language Models.
• Special session webpage: https://sites.google.com/view/emergenn/call-for-papers
• IEEE WCCI 2024 webpage: https://2024.ieeewcci.org/
Contact information:
------------------------------
• Özge Alacam : oezge.alacam@uni-bielefeld.de
• Michiel Straat : mstraat@techfak.uni-bielefeld.de