Papers by Jinyoung Park

10 papers
Can Code-Switched Texts Activate a Knowledge Switch in LLMs? A Case Study on English-Korean Code-Switching (2025.findings-emnlp)

Copied to clipboard

Challenge: Recent large language models (LLMs) demonstrate multilingual abilities, yet they are English-centric due to dominance of English in training corpora.
Approach: They propose to use a synthetic English-korean CS question-answering dataset to investigate this potential.
Outcome: The proposed model can activate, identify and leverage knowledge for reasoning in low-resource languages.
LLM Meets Scene Graph: Can Large Language Models Understand and Generate Scene Graphs? A Benchmark and Empirical Study (2025.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated impressive progress in various text-based tasks, such as question-answering and content generation.
Approach: They propose a benchmark to evaluate Large Language Models’ ability to understand scene graphs and generate them from textual narratives.
Outcome: The proposed model performs well on scene graph understanding but struggles with scene graph generation, particularly for complex narratives.
One Missing Piece for Open-Source Reasoning Models: A Dataset to Mitigate Cold-Starting Short CoT LLMs in RL (2025.acl-industry)

Copied to clipboard

Challenge: Existing large reasoning models are limited by their closed nature and high API costs and safety issues.
Approach: They propose to build a long CoT dataset with existing short CoT LLMs that are not trained for inference-time scaling.
Outcome: The proposed model achieves quality comparable to—or slightly below—R1 and is able to think longer and provide control over the thought budget to better manage the overthinking problem.
Soft Representation Learning for Sparse Transfer (P19-1)

Copied to clipboard

Challenge: Using adversarial training, we can “soft-code” shared and private spaces to avoid sparse sharing.
Approach: They propose to use adversarial training to “soft-code” shared and private spaces to avoid the shared space gets too sparse.
Outcome: The proposed architecture avoids sparse sharing of shared and private spaces, and also deals with low-quality input.
Generative Subgraph Retrieval for Knowledge Graph–Grounded Dialog Generation (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for knowledge graph–grounded dialog generation fail to leverage the rich knowledge of pretrained language models.
Approach: They propose a method for dialog generation that integrates dialog history with a knowledge graph.
Outcome: The proposed method achieves state-of-the-art in knowledge graph–grounded dialog generation on OpenDialKG and KOMODIS datasets.
Less is More: Attention Supervision with Counterfactuals for Text Classification (2020.emnlp-main)

Copied to clipboard

Challenge: Specifically, we explore the advantage of counterfactual reasoning, over associative reasoning . Adding human supervision to attention has been shown to improve model predictions and explanations .
Approach: They propose to use machine-augmented human attention supervision to enhance model quality.
Outcome: The proposed method is more effective than existing methods requiring higher annotation cost . the proposed method can be trained to generate similar attention to human supervision .
Detecting Bipolar Disorder from Misdiagnosed Major Depressive Disorder with Mood-Aware Multi-Task Learning (2024.naacl-long)

Copied to clipboard

Challenge: Bipolar Disorder (BD) is a mental disorder characterized by intense mood swings, ranging from depression to manic states.
Approach: They propose to use social media data to identify BD risk in individuals misdiagnosed as MDD by multi-task learning.
Outcome: The proposed approach outperforms state-of-the-art baselines and can provide insights into the impact of BD mood on future risk.
Cross-Lingual Suicidal-Oriented Word Embedding toward Suicide Prevention (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing suicide dictionaries for other languages have been limited to Korean . a model that uses social media data to identify whether a post includes suicidal ideation is useful .
Approach: They propose a model that uses existing suicide dictionaries for Korean to predict suicidal ideation . they use the existing dictionary for English and Chinese to translate a post into English and then use the separate suicide-oriented embeddings for English.
Outcome: The proposed model can detect whether a given social media post includes suicidal ideation in Korean . it uses existing suicide dictionaries for other languages to translate the post into English and Chinese, and then embeds the suicide-oriented embeddings for English and China.
Learning with Limited Data for Multilingual Reading Comprehension (D19-1)

Copied to clipboard

Challenge: Existing approaches to support question answering in a new language with limited training resources introduce noises to the training data due to translation or generation errors.
Approach: They propose a weakly-supervised framework that quantifies noises from automatically generated labels to deemphasize or fix noisy data in training.
Outcome: The proposed framework can deemphasize or fix noisy data in training on low-resource languages with varying similarity to English.
PAC-BENCH: Evaluating Multi-Agent Collaboration under Privacy Constraints (2026.findings-acl)

Copied to clipboard

Challenge: Recent research explores multi-agent systems where agents collaborate toward shared goals to handle complex tasks.
Approach: They propose a benchmark for systematic evaluation of multi-agent collaboration under privacy constraints.
Outcome: The proposed benchmark shows that privacy constraints degrade collaboration performance and make outcomes depend more on the initiating agent than the partner.

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