===========================================================================================================
ACM Transactions on Intelligent Systems and Technology 2024
Special Issue on Integrating Large Language Models and Knowledge Graphs for Generative AI: Call for Papers
===========================================================================================================

###########Guest Editors:###########
Qi He, Head of AI and VP at Nextdoor, USA, (vela1027@gmail.com), https://www.linkedin.com/in/qi-he/
Wei Wang, Leonard Kleinrock Chair Professor at UCLA, USA, (weiwang@cs.ucla.edu), https://web.cs.ucla.edu/~weiwang/
Hao Wang, Professor at the Norwegian University of Science and Technology and Xidian University, Norway and China, (iswanghao@gmail.com), https://www.ntnu.edu/employees/hawa

###########Special issue information:###########
The integration of Large Language Models (LLMs) and Knowledge Graphs (KGs) represents a cutting-edge research frontier with the potential to revolutionize generative AI capabilities. LLMs, exemplified by GPT and BERT, have demonstrated remarkable text and language understanding capabilities, while KGs excel in storing factual knowledge. This synergy holds the promise of addressing key limitations in both LLMs and KGs and unlocking new horizons in generative AI development.
The field of KGs has matured considerably, offering a reliable repository for structured knowledge and facts with strong interpretability and decision-making capabilities. However, it faces challenges in summarizing information and generating new knowledge based on existing correlations. In contrast, LLMs possess robust language processing and generalization capabilities by parameterizing relationships within knowledge, but their probabilistic nature limits interpretability and creates hallucinations. This unique interdependence offers the opportunity to merge their strengths, enabling the resolution of technical challenges for generative AI, such as constructing comprehensive real-world knowledge, and improving the accuracy of automated responses generated by chatbots.
There are multiple key research directions in merging KGs and LLMs for generative AI. These include enhancing the accuracy of LLMs' knowledge summarization and generation by 1) Enhancing LLMs' accuracy in content generation and question answering by integrating KGs within the procedures of prompt engineering and answer retrieval; 2) Fine-tuning LLMs with KGs as auxiliary labels; and 3) Incorporating KGs into the pre-training stages of LLMs. Concurrently, LLMs can accelerate the construction of KGs by converting unstructured data to structured formats, or by improving text comprehension for tasks associated with KGs. This special issue aims to facilitate the sharing and discussion of recent progress and future trends in the collaborative development of LLMs and KGs for generative AI.

###########Topics:###########
We invite submissions on all topics of Integrating Large Language Models and Knowledge Graphs for Generative AI, including but not limited to:
•Knowledge Graph-Enhanced LLMs: Enhanced pre-training, inferencing, and interpretability in LLMs, along with novel applications
•Ways in Which LLMs Enhance Knowledge Graphs: Such as knowledge extraction, canonicalization, knowledge graph construction, ontological schema construction, and their novel applications
•Collaborative Approaches: Collaborations between LLMs and KGs for bidirectional reasoning driven by both data and knowledge
•Transforming Unstructured Data: Using LLMs to convert unstructured data into structured data for KG generation
•Knowledge Graph Alignment: Utilizing LLMs for alignment tasks in knowledge graphs
•Semantic Alignment: Investigating semantic alignment and knowledge awareness in KG-based LLMs
•Zero-Shot Learning: Applications of LLMs for zero-shot learning in KGs
•Development Potential: Exploring the potential of LLMs within KGs and vice versa
•Mixed Representations: Examining mixed representations of explicit structured knowledge in KGs and parametric knowledge in LLMs
•Evaluation and Benchmarking: Assessing specific domains using LLMs in conjunction with KGs, along with dataset construction methods
•Causal Reasoning: Applications of LLMs and KGs in causal reasoning
•Semantic Search: Utilizing LLMs and KGs for semantic search, question answering, recommendation systems, and more
•Fact Verification: Employing LLMs and KGs for fact verification via reasoning
•Complex Logical Reasoning: Investigating the use of LLMs and KGs in complex logical reasoning tasks
•Feature Interpretation: Exploring methods for interpreting features in LLM-KG models

###########Important Dates:###########
•Submissions deadline: January 31, 2024
•First-round review decisions: April 30, 2024
•Deadline for Minor Revision Submissions: May 31, 2024
•Deadline for Major Revision Submissions: July 31, 2024
•Notification of final decisions: August 31, 2024
•Tentative publication: October 2024

###########Submission Information:###########
Submissions must be prepared according to the TIST submission guidelines (https://dl.acm.org/journal/tist/author-guidelines) and must be submitted via Manuscript Central (https://mc.manuscriptcentral.com/tist). The special issue will also consider extended versions (at least 30% new content) of papers published at conferences.

For questions and further information, please contact Guest Editors: Qi He, Wei Wang, Hao Wang.

More details:https://dl.acm.org/journal/tist/cfp#calls-for-papers