Wonbin Kweon
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Wonbin Kweon has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- Hwanjo Yu
Pohang University of Science and Technology, Pohang, Republic of Korea
12 shared publications - SeongKu Kang
Korea University, Seoul, Republic of Korea
10 shared publications - Jiawei Han
University of Illinois Urbana-Champaign, Urbana, Illinois, USA
4 shared publications - Dongha Lee
Department of Artificial Intelligence, Yonsei University, Seoul, Republic of Korea
3 shared publications - Gyuseok Lee
University of Illinois Urbana-Champaign, Champaign, IL, USA
3 shared publications - Bowen Jin
University of Illinois Urbana-Champaign, United States
2 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2174-2185
From Overlooked to Explored: Recovering Item Relations via Mixture of Perspectives for Sequential Recommendation
Capturing user preference from a user's interaction sequence is the central challenge of Sequential Recommendation (SR). This preference intuitively emerges from inter-item relations: each item transition reflects a preference embedded in the relations between items, making the faithful capture of these relations essential for accurate recommendation. For this reason, self-attention is dominant in sequential recommendation for its ability to compute pairwise item interactions, yet our empirical analysis reveals that it consistently suffers from similarity bias across various types of transformer-based SR models: dot-product attention scores disproportionately favor similar items, systematically overlooking heterogeneous relations with meaningful preference signals and directly limiting recommendation performance. To address this, we propose PRISM (Perspective-based Relational Insight Synthesis Module), a module that re-examines item relations from multiple perspectives. PRISM employs K Perspective Lenses to calibrate attention from distinct viewpoints, combining an Affinity View that refines homogeneous relations and a Contrast View that exposes heterogeneous ones suppressed by similarity bias, enabling the model to capture the full spectrum of user preferences. Extensive experiments on seven real-world benchmarks demonstrate that PRISM consistently outperforms state-of-the-art baselines. Our code is available at https://github.com/327aem/PRISM/.
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2174-2185
Open AccessFrom Overlooked to Explored: Recovering Item Relations via Mixture of Perspectives for Sequential Recommendation
Capturing user preference from a user's interaction sequence is the central challenge of Sequential Recommendation (SR). This preference intuitively emerges from inter-item relations: each item transition reflects a preference embedded in the relations between items, making the faithful capture of these relations essential for accurate recommendation. For this reason, self-attention is dominant in sequential recommendation for its ability to compute pairwise item interactions, yet our empirical analysis reveals that it consistently suffers from similarity bias across various types of transformer-based SR models: dot-product attention scores disproportionately favor similar items, systematically overlooking heterogeneous relations with meaningful preference signals and directly limiting recommendation performance. To address this, we propose PRISM (Perspective-based Relational Insight Synthesis Module), a module that re-examines item relations from multiple perspectives. PRISM employs K Perspective Lenses to calibrate attention from distinct viewpoints, combining an Affinity View that refines homogeneous relations and a Contrast View that exposes heterogeneous ones suppressed by similarity bias, enabling the model to capture the full spectrum of user preferences. Extensive experiments on seven real-world benchmarks demonstrate that PRISM consistently outperforms state-of-the-art baselines. Our code is available at https://github.com/327aem/PRISM/.
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 217-228
SCoRD: Semantic-Assisted Continual Retriever-Reranker Distillation for LLM-Based Recommendation
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 217-228
Open AccessSCoRD: Semantic-Assisted Continual Retriever-Reranker Distillation for LLM-Based Recommendation
- Open Access
- 1 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
Improving Scientific Document Retrieval with Academic Concept Index
Adapting general-domain retrievers to scientific domains is challenging due to the scarcity of large-scale domain-specific relevance annotations and the substantial mismatch in vocabulary and information needs. Recent approaches address these issues through two independent directions that leverage large language models (LLMs): (1) generating synthetic queries for fine-tuning, and (2) generating auxiliary contexts to support relevance matching. However, both directions overlook the diverse academic concepts embedded within scientific documents, often producing redundant or conceptually narrow queries and contexts. To address this limitation, we introduce an academic concept index , which extracts key concepts from papers and organizes them guided by an academic taxonomy. This structured index serves as a foundation for improving both directions. First, we enhance the synthetic query generation with concept coverage-based generation ( CCQGen ), which adaptively conditions LLMs on uncovered concepts to generate complementary queries with broader concept coverage. Second, we strengthen the context augmentation with concept-focused auxiliary contexts ( CCExpand ), which leverages a set of document snippets that serve as concise responses to the concept-aware CCQGen queries. Extensive experiments show that incorporating the academic concept index into both query generation and context augmentation leads to higher-quality queries, better conceptual alignment, and improved retrieval performance.
- 1 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
Open AccessImproving Scientific Document Retrieval with Academic Concept Index
Adapting general-domain retrievers to scientific domains is challenging due to the scarcity of large-scale domain-specific relevance annotations and the substantial mismatch in vocabulary and information needs. Recent approaches address these issues through two independent directions that leverage large language models (LLMs): (1) generating synthetic queries for fine-tuning, and (2) generating auxiliary contexts to support relevance matching. However, both directions overlook the diverse academic concepts embedded within scientific documents, often producing redundant or conceptually narrow queries and contexts. To address this limitation, we introduce an academic concept index , which extracts key concepts from papers and organizes them guided by an academic taxonomy. This structured index serves as a foundation for improving both directions. First, we enhance the synthetic query generation with concept coverage-based generation ( CCQGen ), which adaptively conditions LLMs on uncovered concepts to generate complementary queries with broader concept coverage. Second, we strengthen the context augmentation with concept-focused auxiliary contexts ( CCExpand ), which leverages a set of document snippets that serve as concise responses to the concept-aware CCQGen queries. Extensive experiments show that incorporating the academic concept index into both query generation and context augmentation leads to higher-quality queries, better conceptual alignment, and improved retrieval performance.
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 13334-13338
Structure Shapes the Future of DataxLLM Systems: Retrieval, Structuring, and Reasoning
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 13334-13338
Open AccessStructure Shapes the Future of DataxLLM Systems: Retrieval, Structuring, and Reasoning
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 11774-11785
Condition-Gated Reasoning for Context-Dependent Biomedical Question Answering
Current biomedical question answering (QA) systems often assume that medical knowledge applies uniformly, yet real-world clinical reasoning is inherently conditional: nearly every decision depends on patient-specific factors such as comorbidities and contraindications. Existing benchmarks do not evaluate such conditional reasoning, and retrieval-augmented or graph-based methods lack explicit mechanisms to ensure that retrieved knowledge is applicable to given context. To address this gap, we propose CondMedQA, the first benchmark for conditional biomedical QA, consisting of multi-hop questions whose answers vary with patient conditions. Furthermore, we propose Condition-Gated Reasoning (CGR), a novel framework that constructs condition-aware knowledge graphs and selectively activates or prunes reasoning paths based on query conditions. Our findings show that CGR more reliably selects condition-appropriate answers while matching or exceeding state-of-the-art performance on biomedical QA benchmarks, highlighting the importance of explicitly modeling conditionality for robust medical reasoning.
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 11774-11785
Open AccessCondition-Gated Reasoning for Context-Dependent Biomedical Question Answering
Current biomedical question answering (QA) systems often assume that medical knowledge applies uniformly, yet real-world clinical reasoning is inherently conditional: nearly every decision depends on patient-specific factors such as comorbidities and contraindications. Existing benchmarks do not evaluate such conditional reasoning, and retrieval-augmented or graph-based methods lack explicit mechanisms to ensure that retrieved knowledge is applicable to given context. To address this gap, we propose CondMedQA, the first benchmark for conditional biomedical QA, consisting of multi-hop questions whose answers vary with patient conditions. Furthermore, we propose Condition-Gated Reasoning (CGR), a novel framework that constructs condition-aware knowledge graphs and selectively activates or prunes reasoning paths based on query conditions. Our findings show that CGR more reliably selects condition-appropriate answers while matching or exceeding state-of-the-art performance on biomedical QA benchmarks, highlighting the importance of explicitly modeling conditionality for robust medical reasoning.
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 902-912
SPRINT: Scalable and Predictive Intent Refinement for LLM-Enhanced Session-based Recommendation
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 902-912
Open AccessSPRINT: Scalable and Predictive Intent Refinement for LLM-Enhanced Session-based Recommendation
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1798-1808
Federated Continual Recommendation
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1798-1808
Open AccessFederated Continual Recommendation
- Open Access
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 425-435
Controlling Diversity at Inference: Guiding Diffusion Recommender Models with Targeted Category Preferences
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 425-435
Open AccessControlling Diversity at Inference: Guiding Diffusion Recommender Models with Targeted Category Preferences
- Open Access
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 4889-4901
Uncertainty Quantification and Decomposition for LLM-based Recommendation
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 4889-4901
Open AccessUncertainty Quantification and Decomposition for LLM-based Recommendation
- Open Access
- 22 March 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Recommender Systems
- Vol. 3 (3) , 1-28
Unbiased, Effective, and Efficient Distillation from Heterogeneous Models for Recommender Systems
In recent years, recommender systems have achieved remarkable performance by using ensembles of heterogeneous models. However, this approach is costly due to the resources and inference latency proportional to the number of models, creating a bottleneck for production. Our work aims at transfering the ensemble knowledge of heterogeneous teachers to a lightweight student model using knowledge distillation (KD), reducing inference costs while maintaining high accuracy. We find that the efficacy of distillation decreases when transferring knowledge from heterogeneous teachers. To address this, we propose a new KD framework, named HetComp, that guides the student model by transferring easy-to-hard sequences of knowledge generated from teachers’ trajectories. HetComp uses dynamic knowledge construction to provide progressively difficult ranking knowledge and adaptive knowledge transfer to gradually transfer finer-grained ranking information. Although HetComp improves accuracy, it exacerbates popularity bias, resulting in a high popularity lift. To mitigate this issue, we introduce two strategies that leverage models’ disagreement knowledge (i.e., dissensus) for heterogeneous comparison. Our experiments demonstrate that HetComp significantly enhances distillation quality and the student model’s generalization capabilities. Furthermore, we provide extensive experimental results supporting the effectiveness of our dissensus-based debiasing techniques in mitigating the popularity lift caused by HetComp.
- 22 March 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Recommender Systems
- Vol. 3 (3) , 1-28
Open AccessUnbiased, Effective, and Efficient Distillation from Heterogeneous Models for Recommender Systems
In recent years, recommender systems have achieved remarkable performance by using ensembles of heterogeneous models. However, this approach is costly due to the resources and inference latency proportional to the number of models, creating a bottleneck for production. Our work aims at transfering the ensemble knowledge of heterogeneous teachers to a lightweight student model using knowledge distillation (KD), reducing inference costs while maintaining high accuracy. We find that the efficacy of distillation decreases when transferring knowledge from heterogeneous teachers. To address this, we propose a new KD framework, named HetComp, that guides the student model by transferring easy-to-hard sequences of knowledge generated from teachers’ trajectories. HetComp uses dynamic knowledge construction to provide progressively difficult ranking knowledge and adaptive knowledge transfer to gradually transfer finer-grained ranking information. Although HetComp improves accuracy, it exacerbates popularity bias, resulting in a high popularity lift. To mitigate this issue, we introduce two strategies that leverage models’ disagreement knowledge (i.e., dissensus) for heterogeneous comparison. Our experiments demonstrate that HetComp significantly enhances distillation quality and the student model’s generalization capabilities. Furthermore, we provide extensive experimental results supporting the effectiveness of our dissensus-based debiasing techniques in mitigating the popularity lift caused by HetComp.