MVIGER: Multi-View Variational Integration of Complementary Knowledge for Generative Recommender
cs.IR, cs.AI
Submitted: 2024-08-16
Updated: 2026-04-26
Journal ref: Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '26), pp. 834-844, 2026
Code: https://github.com/gusye1234/LightGCN-PyTorch
License: http://creativecommons.org/licenses/by/4.0/
The gist: Language Models (LMs) have been widely used in recommender systems to incorporate textual information of items into item IDs, leveraging their advanced language understanding and generation
Terminology
Abstract
Language Models (LMs) have been widely used in recommender systems to incorporate textual information of items into item IDs, leveraging their advanced language understanding and generation capabilities. Recently, generative recommender systems have utilized the reasoning abilities of LMs to directly generate index tokens for potential items of interest based on the user's interaction history. To inject diverse item knowledge into LMs, prompt templates with detailed task descriptions and various indexing techniques derived from diverse item information have been explored. This paper focuses on the inconsistency in outputs generated by variations in input prompt templates and item index types, even with the same user's interaction history. Our in-depth quantitative analysis reveals that preference knowledge learned from diverse prompt templates and heterogeneous indices differs significantly, indicating a high potential for complementarity. To fully exploit this complementarity and provide consistent performance under varying prompts and item indices, we propose MVIGER, a unified variational framework that models selection among these information sources as a categorical latent variable with a learnable prior. During inference, this prior enables the model to adaptively select the most relevant source or aggregate predictions across multiple sources, thereby ensuring high-quality recommendation across diverse template-index combinations. We validate the effectiveness of MVIGER on three real-world datasets, demonstrating its superior performance over existing generative recommender baselines through the effective integration of complementary knowledge.
Sources
- Enhancing Item Tokenization for Generative Recommendation through Self-Improvement
- M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systems
- Autoregressive Entity Retrieval
- Session-based Recommendations with Recurrent Neural Networks
- Exploring the Upper Limits of Text-Based Collaborative Filtering Using Large Language Models: Discoveries and Insights
- Bridging Items and Language: A Transition Paradigm for Large Language Model-Based Recommendation
- Decoupled Weight Decay Regularization
- Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models
- LLaMA: Open and Efficient Foundation Language Models
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
- CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendation
- Universal Item Tokenization for Transferable Generative Recommendation
Related papers
- The Price of Isolation: Estimating the Ecosystem Cost of Symmetric Two-Sided A/B Testing
- SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG
- MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora
- RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation
- Right Family, Wrong Skill: Evaluating Risk Exposure in Agent Skill Retrieval
- UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG