Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.
? Tutorial for this page

Verbalizing LightGCN: Direct Learning of Textual Representations from User-Item Interaction Graph via LLMs

sigir26-097 · Full research paper · Manh-Khanh Ngo Huu, Hady Wirawan Lauw
LLM-Collaborative Filtering Integrat · 25% Graph Neural Network Architectures f · 25% User Profile and Persona Modeling · 25% LLM-Derived Knowledge Infusion · 25%
Abstract

In this work, we propose VerbaLightGCN, a novel LLM-based recommendation framework that integrates the semantic understanding of LLMs with user-item interaction modeling. Traditional collaborative filtering (CF) models typically embed user and item IDs into a latent space to capture interaction signals. However, pretrained LLMs cannot natively interpret these learned embeddings. To bridge this gap, VerbaLightGCN adopts a CF-as-text paradigm, in which collaborative signals are encoded in textual form and directly learned from the user–item interaction graph, and are then combined with semantic information to construct user and item profiles that function as latent embeddings. Inspired by LightGCN, our method retains its message-passing design but replaces numerical embedding computations with a Chain-of-Thought prompting mechanism. This enables LLMs to simulate the LightGCN aggregation process through natural language. The result is a recommendation framework that unifies semantic understanding with collaborative signals in a fully language-native form. Experiments show that VerbaLightGCN achieves superior performance to both zero-shot LLM-based and traditional CF-based baselines. Further analysis reveals that the user and item profiles generated by VerbaLightGCN effectively capture both semantic preferences and collaborative filtering signals.

Assigned reviewers

#ReviewerMatchWhy (closest evidence publications in the taxonomy)
1 Huifeng Guo
52
60 Prompt Tuning as User Inherent Profile Inference Machine (2025) Efficiency and Deployment
56 Compressed Interaction Graph based Framework for Multi-behavior Recommendation (2023) Sequential and Session-Based Graph Recommendation
56 SELF: Surrogate-light Feature Selection with Large Language Models in Deep Recommender Systems (2025) LLM-Derived Knowledge Infusion
2 Xiaolong Liu 0012
50
56 DGRec: Graph Neural Network for Recommendation with Diversified Embedding Generation (2023) Graph-based User and Item Representation Learning
55 Collaborative Alignment for Recommendation (2024) Graph Contrastive and Self-Supervised Learning
53 Unified Pretraining for Recommendation via Task Hypergraphs (2024) Graph Neural Network Architectures for CF
3 Jin Chen 0008
49
54 When large language models meet personalization: perspectives of challenges and opportunities (2024) User Profile and Persona Modeling
48 Cooperative Retriever and Ranker in Deep Recommenders (2023) Recommendation with Search and Ranking
48 Learning-Efficient Yet Generalizable Collaborative Filtering for Item Recommendation (2024) Recommendation Systems and Evaluation

Area chair

Area chairMatch
Pengyue Jia 49
Area-chair candidates (7)
Pengyue Jia assigned 4910 papers
Xin Xin 0003 4910 papers
Yankai Chen 0001 476 papers
Maolin Wang 0001 4715 papers
Yanan Niu 4615 papers
Kun Gai 455 papers
Weiming Liu 0005 448 papers

Candidates from the panel ranked by match score

#ReviewerMatchLoadWhy
1 Bo Chen 0023 53 3
74 ELCoRec: Enhance Language Understanding with Co-Propagation of Numerical and Categorical Features for Recommendation (2024) LLM-Collaborative Filtering Integration
67 Full-Stack Optimized Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation (2026) Sequential and Session-based Recommendation
2 Huifeng Guo assigned 52 3
60 Prompt Tuning as User Inherent Profile Inference Machine (2025) Efficiency and Deployment
56 Compressed Interaction Graph based Framework for Multi-behavior Recommendation (2023) Sequential and Session-Based Graph Recommendation
3 Yongjing Hao 51 3
56 How Do Graph Signals Affect Recommendation: Unveiling the Mystery of Low and High-Frequency Graph Signals (2026) Graph-based User and Item Representation Learning
56 Edge-enhanced Global Disentangled Graph Neural Network for Sequential Recommendation (2023) Sequential and Session-Based Graph Recommendation
4 Yang Zhang 0072 50 3
60 AlpsBench: An LLM Personalization Benchmark for Real-Dialogue Memorization and Preference Alignment (2026) Efficiency and Deployment
54 LLM Personalization: Foundations, Breakthroughs, and Frontiers (2026) User Profile and Persona Modeling
5 Xiaolong Liu 0012 assigned 50 3
56 DGRec: Graph Neural Network for Recommendation with Diversified Embedding Generation (2023) Graph-based User and Item Representation Learning
55 Collaborative Alignment for Recommendation (2024) Graph Contrastive and Self-Supervised Learning
6 Jizhi Zhang 50 3
54 Agentic Feedback Loop Modeling Improves Recommendation and User Simulation (2025) User Profile and Persona Modeling
51 Large Language Model Can Interpret Latent Space of Sequential Recommender (2026) Sequential and Session-based Recommendation
7 Jiancan Wu 50 3
56 Graph convolution machine for context-aware recommender system (2022) Graph-based User and Item Representation Learning
56 Large Language Model Can Interpret Latent Space of Sequential Recommender (2026) Sequential and Session-based Recommendation
8 Jieming Zhu 49 3
60 Towards Open-World Recommendation with Knowledge Augmentation from Large Language Models (2024) Knowledge Infusion and Open-World Augmentation
59 Efficient and Deployable Knowledge Infusion for Open-World Recommendations via Large Language Models (2026) Knowledge Infusion and Open-World Augmentation
10 Seongmin Park 0002 49 3
60 LLM-Enhanced Linear Autoencoders for Recommendation (2025) Collaborative-Semantic Representation Alignment
50 Linear Item-Item Models with Neural Knowledge for Session-based Recommendation (2025) Efficient and Long-Sequence Sequential Recommendation
12 Jin Chen 0008 assigned 49 3
54 When large language models meet personalization: perspectives of challenges and opportunities (2024) User Profile and Persona Modeling
48 Cooperative Retriever and Ranker in Deep Recommenders (2023) Recommendation with Search and Ranking
13 Bowen Zheng 0005 49 3
52 Autonomous Reasoning-Retrieval for Large Language Model Based Recommendation (2025) Reasoning-Intensive Retrieval and Ranking
50 Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation (2024) Generative Recommendation and Item Tokenization
14 Jianling Wang 48 3
59 LLMs for User Interest Exploration in Large-scale Recommendation Systems (2024) Sequential and Session-based Recommendation
58 Fresh Content Recommendation at Scale: A Multi-funnel Solution and the Potential of LLMs (2024) Efficiency and Deployment
15 Chongming Gao 48 3
54 Agentic Feedback Loop Modeling Improves Recommendation and User Simulation (2025) User Profile and Persona Modeling
48 On the Theories Behind Hard Negative Sampling for Recommendation (2023) Recommendation Systems and Evaluation
16 Xiao Zhang 0034 48 3
61 Benefit from Rich: Tackling Search Interaction Sparsity in Search Enhanced Recommendation (2025) Recommendation with Search and Ranking
58 Large Language Models Enhanced Collaborative Filtering (2024) Preference Alignment and Optimization
17 Zhengyi Yang 0007 48 3
50 Large Language Model Can Interpret Latent Space of Sequential Recommender (2026) Generative Recommendation and Item Tokenization
47 A Bi-Step Grounding Paradigm for Large Language Models in Recommendation Systems (2025) Generative Recommendation and Item Tokenization
19 Wei Wei 0027 47 3
68 LLMRec: Large Language Models with Graph Augmentation for Recommendation (2024) Graph Pretraining and Foundation Models
54 Representation Learning with Large Language Models for Recommendation (2024) Text Embedding and Representation Learning
21 Yang Song 0008 47 3
72 Large Language Models Enhanced Collaborative Filtering (2024) LLM-Enhanced Collaborative Filtering
56 Sequential Recommendation with Graph Neural Networks (2021) Sequential and Session-Based Graph Recommendation
23 Chen Wang 0052 46 3
57 Unified Pretraining for Recommendation via Task Hypergraphs (2024) Graph Pretraining and Foundation Models
49 Collaborative Alignment for Recommendation (2024) Collaborative-Semantic Representation Alignment
24 Fei Sun 0001 46 3
46 Personalized re-ranking for recommendation (2019) Recommendation with Search and Ranking
46 Neural Re-ranking in Multi-stage Recommender Systems: A Review (2022) Recommendation Systems and Evaluation
25 Noveen Sachdeva 46 3
49 Sequential Variational Autoencoders for Collaborative Filtering (2019) Generative Models for Recommendation and Content › Others
49 ECLARE: Extreme Classification with Label Graph Correlations (2021) Graph Neural Network Architectures for CF
26 Bo Peng 0009 46 3
48 eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale, High-quality Instruction Data (2024) Efficiency and Deployment
48 M2: Mixed Models With Preferences, Popularities and Transitions for Next-Basket Recommendation (2023) Efficient and Long-Sequence Sequential Recommendation
27 Riwei Lai 46 3
60 Multi-Faceted Global Item Relation Learning for Session-Based Recommendation (2022) Graph-Based Sequential and Session Recommendation
46 Proxy-Aware Cross-Domain Sequential Recommendation (2023) Cross-Domain Sequential Recommendation
28 Lingling Yi 46 3
60 TRAWL: External Knowledge-Enhanced Recommendation with LLM Assistance (2025) LLM-Derived Knowledge Infusion
56 PRECISE: Pre-training and Fine-tuning Sequential Recommenders with Collaborative and Semantic Information (2025) Sequential and Session-based Recommendation
29 Qijiong Liu 46 3
60 ONCE: Boosting Content-based Recommendation with Both Open- and Closed-source Large Language Models (2024) LLM-Derived Knowledge Infusion
48 Can LLMs Outshine Conventional Recommenders? A Comparative Evaluation (2025) Efficiency and Deployment
30 Junjie Zhang 0009 46 3
53 STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning (2025) RL Training of Search Agents
52 AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems (2024) RL Training of Search Agents
31 Wei Guo 0006 45 3
56 Compressed Interaction Graph based Framework for Multi-behavior Recommendation (2023) Sequential and Session-Based Graph Recommendation
49 Can LLMs Outshine Conventional Recommenders? A Comparative Evaluation (2025) Efficiency and Deployment
33 Han Li 0005 45 3
50 LEARN: Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Application (2025) Efficiency and Deployment
47 Enhancing Sequential Recommender with Large Language Models for Joint Video and Comment Recommendation (2025) Sequential and Session-based Recommendation
34 Shuchang Liu 0001 45 3
55 Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5) (2022) Knowledge Infusion and Open-World Augmentation
49 DLCRec: A Novel Approach for Managing Diversity in LLM-Based Recommender Systems (2025) Preference Alignment and Optimization
35 Min Hou 0004 45 3
62 STGCN: A Spatial-Temporal Aware Graph Learning Method for POI Recommendation (2020) Graph Neural Network Architectures for CF
49 WeaveRec: An LLM-Based Cross-Domain Sequential Recommendation Framework with Model Merging (2026) Efficiency and Deployment
37 Lianghao Xia 44 3
58 RecLM: Recommendation Instruction Tuning (2025) Preference Alignment and Optimization
51 Self-Supervised Hypergraph Transformer for Recommender Systems (2022) Graph Contrastive and Self-Supervised Learning