Call for Papers
| Submission Deadline | |
| Author notification | |
| Camera ready deadline | |
| Submission server | https://cmt3.research.microsoft.com/KLR2023/ |
| Submission format | Submissions need to be anonymized and should include at most 8 pages, excluding the references and appendices. Please adhere to the ICML 2023 guidelines and style templates. |
We invite submissions that jointly focus on data-driven learning and knowledge, logical, rule-based and commonsense reasoning. They may describe completed research or work-in-progress. Topics of interest include, but are not limited to, the following:
- Trustworthy machine learning using knowledge reasoning, extraction and integration
- Knowledge and logic reasoning for counteracting bias, variance, and uncertainty of data
- Knowledge utilization for efficient data generation and labeling
- Knowledge graphs combined with language and vision models for better generalization
- Natural language reasoning for large language models
- Knowledge graphs for verification of generative models
- Factual grounding and attacking hallucination
- Scaling task and instruction-based fine tuning of LLMs
- Knowledge retrieval, knowledge extraction and knowledge graph construction
- Relational and graph based reasoning
- Contrastive learning for reasoning
- Semantic search and hypothesis discovery
- Automated theorem proving and deductive, abductive and inductive reasoning
- Physical laws and neural networks - geometric deep learning
- Neural algorithmic and logic reasoning
Submissions will be reviewed in a double-blind setting. The workshop is non-archival and will not have any official proceedings. Based on the PC’s recommendation, the accepted papers will be allocated either a contributed talk or a poster presentation. Both in-person and virtual formats will be accommodated for the poster sessions.
We offer a Best Paper Award ($1,000) and several travel grants (complimentary ICML conference registrations).