Papers by Seunguk Yu
From Ground Trust to Truth: Disparities in Offensive Language Judgments on Contemporary Korean Political Discourse (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a recent study using LLMs has relied on outdated datasets and limited generalization ability on unseen texts. |
| Approach: | They construct a large-scale dataset of political discourse and use it to make three judgments . they identify distinct patterns and demonstrate tendencies of label agreement using a leave-one-out strategy. |
| Outcome: | The proposed approach is applicable in real-world settings with inherent constraints. |
UniGen: Universal Domain Generalization for Sentiment Classification via Zero-shot Dataset Generation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Pre-trained language models have limited applicability for inference due to their large parameter size and limited generalization ability. |
| Approach: | They propose a method that generates a dataset regardless of the target domain . this allows for generalization of the tiny task model to any domain that shares the label space . |
| Outcome: | The proposed method achieves generalizability across domains while using a parameter set that is orders of magnitude smaller than PLMs. |
FairQE: Multi-Agent Framework for Mitigating Gender Bias in Translation Quality Estimation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing QE models exhibit systematic gender bias, especially in gender-ambiguous contexts. |
| Approach: | They propose a multi-agent-based, fairness-aware QE framework that mitigates gender bias in both gender-ambiguous and gender-explicit scenarios. |
| Outcome: | The proposed framework mitigates gender bias in gender-ambiguous and gender-explicit scenarios while maintaining the strengths of existing models. |
Don’t be a Fool: Pooling Strategies in Offensive Language Detection from User-Intended Adversarial Attacks (2024.findings-naacl)
Copied to clipboard
| Challenge: | Offensive language detection is important for filtering out abusive expressions, authors argue . authors propose user-intended adversarial attacks that insert special symbols or leverage distinctive features of the Korean language. |
| Approach: | They propose user-intended adversarial attacks that insert special symbols or leverage the distinctive features of the Korean language. |
| Outcome: | The proposed models are more robust to performance degradation even when the attack rate is increased, compared to models trained on noisy texts. |
Delving into Multilingual Ethical Bias: The MSQAD with Statistical Hypothesis Tests for Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Despite recent strides in large language models, studies have highlighted the existence of social biases within them . a recent study examined the ethical biase of LLMs concerning globally discussed topics . |
| Approach: | They propose to validate and compare ethical biases of large language models . they use news articles and socially sensitive questions to generate a data set . |
| Outcome: | The proposed dataset shows that ethical biases are widespread across languages and topics . the null hypothesis was rejected in most cases, suggesting biase arising from language differences. |
Making Sense of Korean Sentences: A Comprehensive Evaluation of LLMs through KoSEnd Dataset (2025.acl-srw)
Copied to clipboard
| Challenge: | Despite advances in LLMs, there are still concerns about their effectiveness with low-resource agglutinative languages compared to English. |
| Approach: | They evaluated 11 LLMs to assess their understanding of Korean sentence endings . they found that explicitly considering linguistic features improved performance . |
| Outcome: | The evaluated LLMs were able to understand Korean sentences better than other languages. |