Jong-Hun Shin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jong-Hun Shin has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Soojong Lim
Electronics and Telecommunications Research Institute, Daejeon, Republic of Korea
4 shared publications - Myeongjin Lee
Electronics and Telecommunications Research Institute, Daejeon, Republic of Korea
3 shared publications - Sanghyun Cho
Electronics and Telecommunications Research Institute, Daejeon, Republic of Korea
3 shared publications - Seung-Hoon Na
Graduate School of Artificial Intelligence, Ulsan National Institute of Science and Technology, Ulsan, Republic of Korea
3 shared publications - Kangil Kim
AI Graduate School Gwangju Institute of Science and Technology
2 shared publications Kiyoung Lee
2 shared publications
Latest Publications
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 3652-3657
From Continuous Pretraining to Domain-Adaptive Reranking via Task Vector Adaptation
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 3652-3657
Open AccessFrom Continuous Pretraining to Domain-Adaptive Reranking via Task Vector Adaptation
- 30 June 2026
- Published by Springer Nature
- p. 191-203
Beyond Semantics: Exploring Context Ranking Under Knowledge Conflicts
- 30 June 2026
- Published by Springer Nature
- p. 191-203
Beyond Semantics: Exploring Context Ranking Under Knowledge Conflicts
- 30 June 2026
- Published by Springer Nature
- p. 204-215
Cloze Your Gaps: Improving Knowledge Extraction via Query Rewriting
- 30 June 2026
- Published by Springer Nature
- p. 204-215
Cloze Your Gaps: Improving Knowledge Extraction via Query Rewriting
- 9 June 2026
- Published by Springer Nature
- p. 263-275
Improving Uncertainty Quantification and Knowledge-Intensive Routing via Query Understanding in Large Language Models
- 9 June 2026
- Published by Springer Nature
- p. 263-275
Improving Uncertainty Quantification and Knowledge-Intensive Routing via Query Understanding in Large Language Models
- Open Access
Do LLMs Need Inherent Reasoning Before Reinforcement Learning? A Study in Korean Self-Correction
Large Language Models (LLMs) demonstrate strong reasoning and self-correction abilities in high-resource languages like English, but their performance remains limited in low-resource languages such as Korean. In this study, we investigate whether reinforcement learning (RL) can enhance Korean reasoning abilities to a degree comparable to English. Our findings reveal that RL alone yields limited improvements when applied to models lacking inherent Korean reasoning capabilities. To address this, we explore several fine-tuning strategies and show that aligning the model's internal reasoning processes with Korean inputs-particularly by tuning Korean-specific neurons in early layers-is key to unlocking RL's effectiveness. We introduce a self-correction code-switching dataset to facilitate this alignment and observe significant performance gains in both mathematical reasoning and self-correction tasks. Ultimately, we conclude that the crucial factor in multilingual reasoning enhancement is not injecting new linguistic knowledge, but effectively eliciting and aligning existing reasoning capabilities. Our study provides a new perspective on how internal translation and neuron-level tuning contribute to multilingual reasoning alignment in LLMs.
Open AccessDo LLMs Need Inherent Reasoning Before Reinforcement Learning? A Study in Korean Self-Correction
Large Language Models (LLMs) demonstrate strong reasoning and self-correction abilities in high-resource languages like English, but their performance remains limited in low-resource languages such as Korean. In this study, we investigate whether reinforcement learning (RL) can enhance Korean reasoning abilities to a degree comparable to English. Our findings reveal that RL alone yields limited improvements when applied to models lacking inherent Korean reasoning capabilities. To address this, we explore several fine-tuning strategies and show that aligning the model's internal reasoning processes with Korean inputs-particularly by tuning Korean-specific neurons in early layers-is key to unlocking RL's effectiveness. We introduce a self-correction code-switching dataset to facilitate this alignment and observe significant performance gains in both mathematical reasoning and self-correction tasks. Ultimately, we conclude that the crucial factor in multilingual reasoning enhancement is not injecting new linguistic knowledge, but effectively eliciting and aligning existing reasoning capabilities. Our study provides a new perspective on how internal translation and neuron-level tuning contribute to multilingual reasoning alignment in LLMs.
- Open Access
- 30 July 2022
- Published by MDPI AG in Electronics
- Vol. 11 (15) , 2390
Toward Understanding Most of the Context in Document-Level Neural Machine Translation
Considerable research has been conducted to obtain translations that reflect contextual information in documents and simultaneous interpretations. Most of the existing studies use concatenation data which merge previous and current sentences for training translation models. Although this corpus improves the performance of the model, ignoring the contextual correlation between the sentences can disturb translation performance. In this study, we introduce a simple and effective method to capture the contextual correlation of the sentence at the document level of the current sentence, thereby learning an effective contextual representation. In addition, the proposed model structure is applied to a separate residual connection network to minimize the loss of the beneficial influence of incorporating the context. The experimental results show that our methods improve the translation performance in comparison with the state-of-the-art baseline of the Transformer in various translation tasks and two benchmark machine translation tasks.
- 30 July 2022
- Published by MDPI AG in Electronics
- Vol. 11 (15) , 2390
Open AccessToward Understanding Most of the Context in Document-Level Neural Machine Translation
Considerable research has been conducted to obtain translations that reflect contextual information in documents and simultaneous interpretations. Most of the existing studies use concatenation data which merge previous and current sentences for training translation models. Although this corpus improves the performance of the model, ignoring the contextual correlation between the sentences can disturb translation performance. In this study, we introduce a simple and effective method to capture the contextual correlation of the sentence at the document level of the current sentence, thereby learning an effective contextual representation. In addition, the proposed model structure is applied to a separate residual connection network to minimize the loss of the beneficial influence of incorporating the context. The experimental results show that our methods improve the translation performance in comparison with the state-of-the-art baseline of the Transformer in various translation tasks and two benchmark machine translation tasks.
- Open Access
- 26 January 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (3) , 1313
Impact of Sentence Representation Matching in Neural Machine Translation
Most neural machine translation models are implemented as a conditional language model framework composed of encoder and decoder models. This framework learns complex and long-distant dependencies, but its deep structure causes inefficiency in training. Matching vector representations of source and target sentences improves the inefficiency by shortening the depth from parameters to costs and generalizes NMTs with a different perspective to cross-entropy loss. In this paper, we propose matching methods to derive the cost based on constant word-embedding vectors of source and target sentences. To find the best method, we analyze the impact of the methods with varying structures, distance metrics, and model capacity in a French to English translation task. An optimally configured method is applied to English translation tasks from and to French, Spanish, and German. In the tasks, the method showed performance improvement by 3.23 BLEU at maximum, with an improvement of 0.71 on average. We evaluated the robustness of this method to various embedding distributions and models, such as conventional gated structures and transformer networks, and empirical results showed that it has a higher chance to improve performance in those models.
- 26 January 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (3) , 1313
Open AccessImpact of Sentence Representation Matching in Neural Machine Translation
Most neural machine translation models are implemented as a conditional language model framework composed of encoder and decoder models. This framework learns complex and long-distant dependencies, but its deep structure causes inefficiency in training. Matching vector representations of source and target sentences improves the inefficiency by shortening the depth from parameters to costs and generalizes NMTs with a different perspective to cross-entropy loss. In this paper, we propose matching methods to derive the cost based on constant word-embedding vectors of source and target sentences. To find the best method, we analyze the impact of the methods with varying structures, distance metrics, and model capacity in a French to English translation task. An optimally configured method is applied to English translation tasks from and to French, Spanish, and German. In the tasks, the method showed performance improvement by 3.23 BLEU at maximum, with an improvement of 0.71 on average. We evaluated the robustness of this method to various embedding distributions and models, such as conventional gated structures and transformer networks, and empirical results showed that it has a higher chance to improve performance in those models.
- Open Access
- 28 October 2021
- Published by Wiley in ETRI Journal
- Vol. 43 (5) , 775-786
Simultaneous neural machine translation with a reinforced attention mechanism
- 28 October 2021
- Published by Wiley in ETRI Journal
- Vol. 43 (5) , 775-786
Open AccessSimultaneous neural machine translation with a reinforced attention mechanism
- Open Access
- 21 April 2021
- Published by MDPI AG in Electronics
- Vol. 10 (9) , 989
Revisiting Dropout: Escaping Pressure for Training Neural Networks with Multiple Costs
A common approach to jointly learn multiple tasks with a shared structure is to optimize the model with a combined landscape of multiple sub-costs. However, gradients derived from each sub-cost often conflicts in cost plateaus, resulting in a subpar optimum. In this work, we shed light on such gradient conflict challenges and suggest a solution named Cost-Out, which randomly drops the sub-costs for each iteration. We provide the theoretical and empirical evidence of the existence of escaping pressure induced by the Cost-Out mechanism. While simple, the empirical results indicate that the proposed method can enhance the performance of multi-task learning problems, including two-digit image classification sampled from MNIST dataset and machine translation tasks for English from and to French, Spanish, and German WMT14 datasets.
- 21 April 2021
- Published by MDPI AG in Electronics
- Vol. 10 (9) , 989
Open AccessRevisiting Dropout: Escaping Pressure for Training Neural Networks with Multiple Costs
A common approach to jointly learn multiple tasks with a shared structure is to optimize the model with a combined landscape of multiple sub-costs. However, gradients derived from each sub-cost often conflicts in cost plateaus, resulting in a subpar optimum. In this work, we shed light on such gradient conflict challenges and suggest a solution named Cost-Out, which randomly drops the sub-costs for each iteration. We provide the theoretical and empirical evidence of the existence of escaping pressure induced by the Cost-Out mechanism. While simple, the empirical results indicate that the proposed method can enhance the performance of multi-task learning problems, including two-digit image classification sampled from MNIST dataset and machine translation tasks for English from and to French, Spanish, and German WMT14 datasets.
- Open Access
- 1 January 2019
- Published by Association for Computational Linguistics (ACL)
- p. 95-103
JBNU at MRP 2019: Multi-level Biaffine Attention for Semantic Dependency Parsing
Seung-Hoon Na, Jinwoon Min, Kwanghyeon Park, Jong-Hun Shin, Young-Kil Kim. Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning. 2019.
- 1 January 2019
- Published by Association for Computational Linguistics (ACL)
- p. 95-103
Open AccessJBNU at MRP 2019: Multi-level Biaffine Attention for Semantic Dependency Parsing
Seung-Hoon Na, Jinwoon Min, Kwanghyeon Park, Jong-Hun Shin, Young-Kil Kim. Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning. 2019.