4 papers
Personalized Reward Modeling for Text-to-Image Generation
Jeongeun Lee, Ryang Heo, Dongha Lee
Recent text-to-image (T2I) models generate semantically coherent images from textual prompts, yet evaluating how well they align with individual user preferences remains an open ch…
Can Large Language Models be Effective Online Opinion Miners?
Ryang Heo, Yongsik Seo, Junseong Lee +1
The surge of user-generated online content presents a wealth of insights into customer preferences and market trends. However, the highly diverse, complex, and context-rich nature…
Imagine All The Relevance: Scenario-Profiled Indexing with Knowledge Expansion for Dense Retrieval
Sangam Lee, Ryang Heo, SeongKu Kang +1
Existing dense retrieval models struggle with reasoning-intensive retrieval task as they fail to capture implicit relevance that requires reasoning beyond surface-level semantic in…
Make Compound Sentences Simple to Analyze: Learning to Split Sentences for Aspect-based Sentiment Analysis
Yongsik Seo, Sungwon Song, Ryang Heo +2
In the domain of Aspect-Based Sentiment Analysis (ABSA), generative methods have shown promising results and achieved substantial advancements. However, despite these advancements,…