Papers by Dongjun Lee

6 papers
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

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

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations