SangKeun Lee

PICTURE: Enhancing Theory-of-Mind in Large Language Models by Revealing, Not Hiding, Characters’ Lack of Knowledge ACL 2026 Bridging the Gap Between Molecule and Textual Descriptions via Substructure-aware Alignment EMNLP 2025 Connecting the Knowledge Dots: Retrieval-augmented Knowledge Connection for Commonsense Reasoning EMNLP 2025 Curriculum Debiasing: Toward Robust Parameter-Efficient Fine-Tuning Against Dataset Biases ACL 2025 Forward Knows Efficient Backward Path: Saliency-Guided Memory-Efficient Fine-tuning of Large Language Models ACL 2025 “Going to a trap house” conveys more fear than “Going to a mall”: Benchmarking Emotion Context Sensitivity for LLMs EMNLP 2025 Incorporating Domain Knowledge into Materials Tokenization ACL 2025 Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean ACL 2025 Coconut: Contextualized Commonsense Unified Transformers for Graph-Based Commonsense Augmentation of Language Models ACL 2024 KOMBO: Korean Character Representations Based on the Combination Rules of Subcharacters ACL 2024 MELT: Materials-aware Continued Pre-training for Language Model Adaptation to Materials Science EMNLP 2024 Mentor-KD: Making Small Language Models Better Multi-step Reasoners EMNLP 2024 Moleco: Molecular Contrastive Learning with Chemical Language Models for Molecular Property Prediction EMNLP 2024 MolTRES: Improving Chemical Language Representation Learning for Molecular Property Prediction EMNLP 2024 SEED: Semantic Knowledge Transfer for Language Model Adaptation to Materials Science EMNLP 2024 SparseFlow: Accelerating Transformers by Sparsifying Information Flows ACL 2024 Towards Robust and Generalized Parameter-Efficient Fine-Tuning for Noisy Label Learning ACL 2024 Zero-shot Commonsense Reasoning over Machine Imagination EMNLP 2024 Client-Customized Adaptation for Parameter-Efficient Federated Learning ACL 2023 DIVE: Towards Descriptive and Diverse Visual Commonsense Generation EMNLP 2023 Dynamic Structure Pruning for Compressing CNNs AAAI 2023 Examining Consistency of Visual Commonsense Reasoning based on Person Grounding IJCNLP 2023 Improving Bias Mitigation through Bias Experts in Natural Language Understanding EMNLP 2023 Leap-of-Thought: Accelerating Transformers via Dynamic Token Routing EMNLP 2023 SMoP: Towards Efficient and Effective Prompt Tuning with Sparse Mixture-of-Prompts EMNLP 2023 “Why do I feel offended?” - Korean Dataset for Offensive Language Identification EACL 2023 Break it Down into BTS: Basic, Tiniest Subword Units for Korean EMNLP 2022 Efficient Pre-training of Masked Language Model via Concept-based Curriculum Masking EMNLP 2022 Learning from Missing Relations: Contrastive Learning with Commonsense Knowledge Graphs for Commonsense Inference ACL 2022 Tutoring Helps Students Learn Better: Improving Knowledge Distillation for BERT with Tutor Network EMNLP 2022 Handling Out-Of-Vocabulary Problem in Hangeul Word Embeddings EACL 2021 KOAS: Korean Text Offensiveness Analysis System EMNLP 2021 Adaptive Compression of Word Embeddings ACL 2020 Multi-pretraining for Large-scale Text Classification EMNLP 2020 Adaptive Convolution for Text Classification NAACL 2019 Learning to Generate Word Representations using Subword Information COLING 2018