Papers by Juhwan Choi
Enhancing Effectiveness and Robustness in a Low-Resource Regime via Decision-Boundary-aware Data Augmentation (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods to augment textual data are limited due to the discrete characteristics of the textual dataset. |
| Approach: | They propose a decision-boundary-aware data augmentation strategy to enhance robustness using pretrained language models by shifting latent features closer to the decision boundary and reconstruction to generate an ambiguous version with a soft label. |
| Outcome: | The proposed method performs better than existing methods and is extensible with curriculum data augmentation. |
CoBA: Counterbias Text Augmentation for Mitigating Various Spurious Correlations via Semantic Triples (2025.emnlp-main)
Copied to clipboard
| Challenge: | Spurious correlations are patterns that appear in datasets but do not represent genuine relationships. |
| Approach: | They propose a more general form of counterfactual data augmentation that tackles multiple biases . they propose 'CoBA' that decomposes text into subject-predicate-object triples and modifies them to disrupt spurious correlations. |
| Outcome: | The proposed framework reduces biases and strengthens out-of-distribution resilience. |
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. |
Position Paper: How Should We Responsibly Adopt LLMs in the Peer Review Process? (2026.findings-eacl)
Copied to clipboard
| Challenge: | a recent paper criticizes the current use of Large Language Models (LLMs) for simple review text generation. |
| Approach: | They propose to use Large Language Models to support key aspects of the review process . they argue that this approach overlooks more meaningful applications of LLMs . authors argue that the increased reviewing burden per reviewer is a factor . |
| Outcome: | The proposed approach would support reproducibility, correctness and relevance of citations and ethics review flagging. |
Multi-News+: Cost-efficient Dataset Cleansing via LLM-based Data Annotation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Various attempts to correct noisy data in the construction process have been made, but human annotation is expensive and time-consuming. |
| Approach: | They propose to use large language models for data annotation to imitate human annotation and classify unrelated documents from a multi-document summarization task. |
| Outcome: | The proposed method imitates human annotation and classifies unrelated documents from the Multi-News dataset. |
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. |
Plug-in and Fine-tuning: Bridging the Gap between Small Language Models and Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) are renowned for their extensive linguistic knowledge and strong generalization capabilities, but their high computational demands make them unsuitable for resource-constrained environments. |
| Approach: | They propose a framework that integrates a single frozen layer from an LLM into a SLM and fine-tunes the combined model for specific tasks. |
| Outcome: | The proposed framework improves performance across a range of natural language processing tasks, including both natural language understanding and generation. |
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. |
Beyond Single-User Dialogue: Assessing Multi-User Dialogue State Tracking Capabilities of Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models have demonstrated remarkable performance in zero-shot dialogue state tracking (DST), reducing the need for task-specific training. |
| Approach: | They extend existing DST dataset by generating utterances of a second user based on speech act theory. |
| Outcome: | The proposed model incorporates utterances of a second user into conversations, enabling a controlled evaluation of LLMs in multi-user settings. |
See-Saw Modality Balance: See Gradient, and Sew Impaired Vision-Language Balance to Mitigate Dominant Modality Bias (2025.naacl-long)
Copied to clipboard
| Challenge: | Vision-language models often rely on a single modality rather than treating and utilizing them equally, leading to dominance of a specific modality on the overall performance. |
| Approach: | They propose a framework to mitigate dominant modality bias by adjusting the gradient of KL divergence based on each modality's contribution and aligning task directions in a non-conflicting manner. |
| Outcome: | The proposed framework mitigates dominant modality bias on UPMC Food-101, Hateful Memes, and MM-IMDb datasets. |
GPTs Are Multilingual Annotators for Sequence Generation Tasks (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing methods of data annotation are time-consuming and expensive . complexity of crowdsourcing increases when dealing with low-resource languages . |
| Approach: | They propose an autonomous method to gather unlabeled data and label them using large language models. |
| Outcome: | The proposed method is cost-efficient and applicable for low-resource language annotation. |
AutoAugment Is What You Need: Enhancing Rule-based Augmentation Methods in Low-resource Regimes (2024.eacl-srw)
Copied to clipboard
| Challenge: | Existing methods for text data augmentation suffer from potential semantic damage due to the discrete nature of sentences. |
| Approach: | They propose to adapt AutoAugment to solve this problem by using softEDA to increase text data. |
| Outcome: | The proposed method can boost existing augmentation methods and enhance cutting-edge pretrained language models. |