Guest Editor(s)
Prof. Mucheol Kim
Email: kimm@cau.ac.kr
Affiliation: School of Computer Science and Engineering, Chung-Ang University, Seoul, Republic of Korea
Homepage:
Research Interests: language model, graph neural networks, information retrieval, data science
Summary
Neural models have driven major advances in natural language and speech processing by learning rich language representations from large-scale pretraining. Despite their strong performance across languages, domains, and tasks, their decision-making processes often remain difficult to interpret, and the mechanisms underlying their predictions are still not fully understood.
This Special Issue invites contributions on the analysis, explanation, and evaluation of NLP systems. We welcome work on interpretability, probing, explanation generation, reasoning transparency, accountability, and safety, with the goal of improving our understanding of neural models' linguistic abilities, decision processes, and limitations. Original research articles, surveys, and resource papers are all encouraged.
Topics of interest include, but are not limited to:
· Decision explanation methods for neural NLP models
· Probing and diagnostic methods for neural representations
· Methods for distinguishing encoded and used information
· Cross-disciplinary approaches inspired by linguistics, cognitive science, and related fields
· Bias analysis in neural language models
· Prompting- and generation-based explanation methods
· Controlled languages, minimal pairs, and linguistically motivated test suites
· Evaluation of explanation methods, including faithfulness and usefulness
· NLP applications related to explainability, transparency, and responsible AI
Keywords
explainable NLP, model understanding, causal analysis, actionable explanations, trustworthy AI
Login
Register
Submit a Paper
Propose a Special lssue