Papers by Dongjun Kim
Selective Span-Level Unlearning for Large Language Models (2026.acl-short)
Copied to clipboard
| Challenge: | Existing selective methods that focus on identifying token-level or span-level unlearning targets are misaligning unlearning objectives with the model’s internal behavior. |
| Approach: | They propose a selective method that uses model-intrinsic information to identify token-level or span-level unlearning targets within a text rather than entire sequences. |
| Outcome: | The proposed method achieves comparable unlearning performance while significantly better preserving retained knowledge. |
LangSAE Editing: Improving Multilingual Information Retrieval via Post-hoc Language Identity Removal (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for dense retrieval in multilingual environments encode language identity alongside semantics. |
| Approach: | They propose a method that trains on pooled embeddings to remove language-identity signal directly in vector space. |
| Outcome: | The proposed method improves ranking quality and cross-language coverage across multiple languages with especially strong gains for script-distinct languages. |
MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generation (2025.coling-main)
Copied to clipboard
| Challenge: | Recent advances in large language models have enabled in-context learning (ICL)-based methods to outperform fine-tuning approaches for text-to-SQL tasks. |
| Approach: | They propose a method that leverages multiple prompts to explore a broader search space for possible answers and effectively aggregate them. |
| Outcome: | The proposed method achieves execution accuracies of 65.5% and 89.6% on BIRD and Spider benchmarks. |
Enhancing Automatic Term Extraction with Large Language Models via Syntactic Retrieval (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have improved IE, but their potential for ATE has not been explored. |
| Approach: | They propose a retrieval-based prompting strategy that selects demonstrations according to syntactic rather than semantic similarity in a few-shot setting. |
| Outcome: | The proposed method improves performance on three specialized ATE benchmarks. |
Korean Bio-Medical Corpus (KBMC) for Medical Named Entity Recognition (2024.lrec-main)
Copied to clipboard
Sungjoo Byun, Jiseung Hong, Sumin Park, Dongjun Jang, Jean Seo, Minseok Kim, Chaeyoung Oh, Hyopil Shin
| Challenge: | Named Entity Recognition (NER) plays a pivotal role in medical Natural Language Processing (NLP) yet, there is no open-source medical NER dataset specifically for Korean. |
| Approach: | They used ChatGPT to construct an open-source Korean NER dataset . they found 20% increase in medical NER performance compared to general Korean ner datasets. |
| Outcome: | The KBMC dataset shows an impressive 20% increase in medical NER performance compared to models trained on general Korean NER datasets. |
KoLEG: On-the-Fly Korean Legal Knowledge Editing with Continuous Retrieval (2025.findings-emnlp)
Copied to clipboard
Jaehyung Seo, Dahyun Jung, Jaewook Lee, Yongchan Chun, Dongjun Kim, Hwijung Ryu, Donghoon Shin, Heuiseok Lim
| Challenge: | a recent study shows that Korean legal knowledge is subject to frequent temporal updates driven by societal needs and government policies. |
| Approach: | They propose a Korean Legal knowledge editing framework enhanced with continuous retrieval . they employ an Editing-Aware Learning Strategy and a LawEdit Retriever . |
| Outcome: | a new framework outperforms existing methods for updating legal knowledge in Korean . it maintains robust performance in sequential editing and is qualitatively validated by legal experts. |
MMAC: A Multilingual, Multimodal Alignment Framework for Cultural Grounding Evaluation (2026.acl-long)
Copied to clipboard
Weihua Zheng, Zhengyuan Liu, Tanmoy Chakraborty, Weiwen Xu, Xiaoxue Gao, Bryan Chen Zhengyu Tan, Bowei Zou, Chang Liu, Yujia Hu, Xing Xie, Xiaoyuan Yi, Jing Yao, Chaojun Wang, Long Li, Rui Liu, Huiyao Liu, Koji Inoue, Ryuichi Sumida, Tatsuya Kawahara, Fan Xu, Lingyu Ye, Wei Tian, Dongjun Kim, Jimin Jung, Jaehyung Seo, Nadya Yuki Wangsajaya, Pham Minh Duc, Ojasva Saxena, Palash Nandi, Xiyan Tao, Wiwik Karlina, Tuan Luong, Keertana Arun Vasan, Roy Ka-Wei Lee, Nancy F. Chen
| Challenge: | Existing models lack cultural alignment across modalities and languages . a new framework to assess cultural awareness across linguistics and languages is needed . |
| Approach: | They propose a framework that integrates tri-modally aligned cultural benchmarks and a five-dimensional evaluation protocol to assess cross-country awareness disparities. |
| Outcome: | The proposed framework assesses cultural awareness disparities across modalities and languages . it is the first dataset aligned at the input level across text, image, and speech . |
Benchmark Profiling: Mechanistic Diagnosis of LLM Benchmarks (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models are often judged by their scores on standard benchmarks, yet such scores often overstate real capability since they mask the mix of skills a task actually demands. |
| Approach: | They propose a diagnostic framework that decomposes benchmark performance into ten cognitively grounded abilities and computes an Ability Impact Score (AIS) AIS quantifies how much each ability contributes to a model’s success on a given benchmark. |
| Outcome: | The proposed framework decomposes performance into ten cognitively grounded abilities and computes an Ability Impact Score (AIS) that quantifies how much each ability contributes to a model’s success on a given benchmark. |
Enhancing Self-Attention via Knowledge Fusion: Deriving Sentiment Lexical Attention from Semantic-Polarity Scores (2024.starsem-1)
Copied to clipboard
| Challenge: | Existing methods to inject lexical features into self-attention mechanisms have shown remarkable performance across various downstream tasks in NLP. |
| Approach: | They propose to inject lexical features into the self-attention mechanism of Transformer-based models by injecting lexicon-based Sentiment Lexical Attention into the attention scores throughout the training process. |
| Outcome: | The proposed method shows significant performance improvements on the NSMC sentiment classification benchmark and is able to perform in out-of-domain tasks. |
Exploring Coding Spot: Understanding Parametric Contributions to LLM Coding Performance (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated proficiency in code generation and comprehension across multiple programming languages. |
| Approach: | They propose a parameter-localized subset of LLMs that facilitates coding capabilities. |
| Outcome: | The proposed model significantly improves performance on coding tasks while preserving non-coding functionalities. |
Multimodal UNcommonsense: From Odd to Ordinary and Ordinary to Odd (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Multimodal UNcommonsense (MUN) is a benchmark designed to evaluate models’ ability to handle scenarios that deviate from typical visual or contextual expectations. |
| Approach: | They propose a retrieval-based in-context learning framework that transfers reasoning capabilities from larger models to smaller ones without additional training. |
| Outcome: | The proposed method improves on baseline ICL methods by 8.3% over previous methods. |