Papers by Dongjun Lee
Persona Dynamics: Unveiling the Impact of Persona Traits on Agents in Text-Based Games (2025.acl-long)
Copied to clipboard
| Challenge: | Text-based interactive environments have long presented formidable challenges for AI. |
| Approach: | They propose a method for projecting human personality traits onto agents to guide their behavior and integrate them into their policy-learning pipelines. |
| Outcome: | The proposed method induces personality in a text-based game agent by integrating personality profiles directly into the agent's policy-learning pipeline. |
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. |
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 . |
IntelliCAT: Intelligent Machine Translation Post-Editing with Quality Estimation and Translation Suggestion (2021.acl-demo)
Copied to clipboard
| Challenge: | Existing computer-aided translation tools require the translator to edit incorrect parts of a document, while ITP tools require fewer edits. |
| Approach: | They propose an interactive translation interface with neural models that streamline the post-editing process on machine translation output. |
| Outcome: | The proposed interface can significantly improve translation quality and a user study shows that it speeds up the post-editing process by 52.9% compared to translating from scratch. |
Clause-Wise and Recursive Decoding for Complex and Cross-Domain Text-to-SQL Generation (D19-1)
Copied to clipboard
| Challenge: | Existing deep learning approaches for text-to-SQL generation are limited to the WikiSQl dataset . a novel clause-wise decoding neural network model can be used to generate complex queries over multiple databases . |
| Approach: | They propose a SQL clause-wise decoding neural architecture with a schema encoder to address the Spider task. |
| Outcome: | The proposed model achieves 4.6% accuracy gain on the Spider dataset and 9.8% accuracy gain in test and dev sets. |