Jimyeung Seo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Jimyeung Seo has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Byungkook Oh
Konkuk University, Seoul, Republic of Korea
4 shared publications - Dongcheon Lee
Konkuk University, Seoul, Republic of Korea
3 shared publications - Hye-Yoon Baek
Konkuk University, Seoul, Republic of Korea
3 shared publications - Jinho Choi
Konkuk University, Seoul, Republic of Korea
2 shared publications - Xiongnan Jin
Shenzhen University, Shenzhen, China
2 shared publications - Eun-Yeong Jo
Konkuk University, Seoul, Republic of Korea
1 shared publication
Latest Publications
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 2273-2284
Diversifying Differentiable Graph Retrieval with Topic-Adaptive Multi-Intent Learning
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 2273-2284
Open AccessDiversifying Differentiable Graph Retrieval with Topic-Adaptive Multi-Intent Learning
- Open Access
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 574-584
Image-Guided Debiasing Distillation with Preference Alignment Across Multi-News Histories
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 574-584
Open AccessImage-Guided Debiasing Distillation with Preference Alignment Across Multi-News Histories
- Open Access
- 12 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 194229-194244
Interaction-Grounded Semantic Graph Refinement for LLM-Based Recommendation
Large language models (LLMs) have recently demonstrated remarkable potential for recommendation by reframing it as a text-generation task. Recent LLM-based approaches apply GNNs to capture higher-order collaborative patterns from interaction graphs but handle textual data separately, failing to extract higher-order semantic patterns from text. One potential solution is to construct semantic graphs to better capture such semantic relationships. However, naively selecting top-k connections by profile similarity introduces significant challenges: 1) preference gap between textual similarity and actual user behavior, and 2) semantic distortion where identical attributes carry different meanings for users versus items. To overcome these issues, we propose an Interaction-Grounded Semantic Recommender (IGSRec), which constructs an interaction-grounded semantic graph by aligning profile-based connections with observed interactions. IGSRec employs an LLM-based profile generator, constructs a top-k semantic graph, then refines it using a learnable scoring function that identifies relevant semantic neighborhoods conditioned on user-item interactions. Through dual-graph propagation over both the refined semantic and interaction graphs, IGSRec captures higher-order semantic and collaborative patterns. Experiments on Amazon Review benchmarks demonstrate state-of-the-art performance in both direct and sequential recommendation tasks. Our code and data are publicly available at https://github.com/oseoko/IGSRec/.
- 12 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 194229-194244
Open AccessInteraction-Grounded Semantic Graph Refinement for LLM-Based Recommendation
Large language models (LLMs) have recently demonstrated remarkable potential for recommendation by reframing it as a text-generation task. Recent LLM-based approaches apply GNNs to capture higher-order collaborative patterns from interaction graphs but handle textual data separately, failing to extract higher-order semantic patterns from text. One potential solution is to construct semantic graphs to better capture such semantic relationships. However, naively selecting top-k connections by profile similarity introduces significant challenges: 1) preference gap between textual similarity and actual user behavior, and 2) semantic distortion where identical attributes carry different meanings for users versus items. To overcome these issues, we propose an Interaction-Grounded Semantic Recommender (IGSRec), which constructs an interaction-grounded semantic graph by aligning profile-based connections with observed interactions. IGSRec employs an LLM-based profile generator, constructs a top-k semantic graph, then refines it using a learnable scoring function that identifies relevant semantic neighborhoods conditioned on user-item interactions. Through dual-graph propagation over both the refined semantic and interaction graphs, IGSRec captures higher-order semantic and collaborative patterns. Experiments on Amazon Review benchmarks demonstrate state-of-the-art performance in both direct and sequential recommendation tasks. Our code and data are publicly available at https://github.com/oseoko/IGSRec/.
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 109-118
Relation-Faceted Graph Pooling with LLM Guidance for Dynamic Span-Aware Information Extraction
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 109-118
Open AccessRelation-Faceted Graph Pooling with LLM Guidance for Dynamic Span-Aware Information Extraction