← Search

Kang-Min Kim

7 accepted papers

2025

Conflict and Overlap Classification in Construction Standards Using a Large Language Model

NAACL 2025industry

Construction standards across different countries provide technical guidelines to ensure the quality and safety of buildings and facilities, with periodic revisions to accommodate advances in construction technology. However, these standards often contain overlapping or conflicting content owing to…

Cited by 0SourcePDFScholar
2025

Leveraging Knowledge Graph-Enhanced LLMs for Context-Aware Medical Consultation

EMNLP 2025

Recent advancements in large language models have significantly influenced the field of online medical consultations. However, critical challenges remain, such as the generation of hallucinated information and the integration of up-to-date medical knowledge. To address these issues, we propose **I**

2024

Large Language Models are Students at Various Levels: Zero-shot Question Difficulty Estimation

EMNLP 2024finding

Recent advancements in educational platforms have emphasized the importance of personalized education. Accurately estimating question difficulty based on the ability of the student group is essential for personalized question recommendations. Several studies have focused on predicting question diffi…

Cited by 4SourcePDFScholar
2022

Efficient Pre-training of Masked Language Model via Concept-based Curriculum Masking

EMNLP 2022main

Self-supervised pre-training has achieved remarkable success in extensive natural language processing tasks. Masked language modeling (MLM) has been widely used for pre-training effective bidirectional representations but comes at a substantial training cost. In this paper, we propose a novel concep…

2022

Learning from Missing Relations: Contrastive Learning with Commonsense Knowledge Graphs for Commonsense Inference

ACL 2022findings

Commonsense inference poses a unique challenge to reason and generate the physical, social, and causal conditions of a given event. Existing approaches to commonsense inference utilize commonsense transformers, which are large-scale language models that learn commonsense knowledge graphs. However, t…

2021

KOAS: Korean Text Offensiveness Analysis System

EMNLP 2021system demonstrations

Warning: This manuscript contains a certain level of offensive expression. As communication through social media platforms has grown immensely, the increasing prevalence of offensive language online has become a critical problem. Notably in Korea, one of the countries with the highest Internet usage…