Unleash LLMs Potential for Sequential Recommendation by Coordinating Dual Dynamic Index Mechanism
cs.IR, cs.AI, cs.CL, cs.LG
Submitted: 2024-09-14
Updated: 2026-09-16
License: http://creativecommons.org/licenses/by/4.0/
The gist: Owing to the unprecedented capability in semantic understanding and logical reasoning, large language models (LLMs) have shown fantastic potential in developing next-generation sequential recommender
Terminology
Abstract
Owing to the unprecedented capability in semantic understanding and logical reasoning, large language models (LLMs) have shown fantastic potential in developing next-generation sequential recommender systems (RSs). However, existing LLM-based sequential RSs mostly separate index generation from sequential recommendation, leading to insufficient integration between semantic information and collaborative information. On the other hand, the neglect of user-related information hinders LLM-based sequential RSs from exploiting high-order user-item interaction patterns. In this paper, we propose the End-to-End Dual Dynamic (ED squared) recommender, the first LLM-based sequential RS which adopts dual dynamic index mechanism, targeting resolving the above limitations simultaneously. The dual dynamic index mechanism can not only assembly index generation and sequential recommendation into a unified LLM-backbone pipeline, but also make it practical for LLM-based sequential recommender to take advantage of user-related information. Specifically, to facilitate the LLM comprehension ability to dual dynamic index, we propose a multigrained token regulator which constructs alignment supervision based on LLMs semantic knowledge across multiple representation granularities. Moreover, the associated user collection data and a series of novel instruction tuning tasks are specially customized to capture the high-order user-item interaction patterns. Extensive experiments on three public datasets demonstrate the superiority of ED squared, achieving an average improvement of 19.62% in Hit-Rate and 21.11% in NDCG.
Sources
- M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systems
- CoST: Contrastive Quantization based Semantic Tokenization for Generative Recommendation
- MMGRec: Multimodal Generative Recommendation with Transformer Model
- Learnable Item Tokenization for 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