LLM-Augmented Semantic Resonance System (SRR): A Unified Triple-Objective Architecture for Deep Sequential Recommendation
- 5 January 2026
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 588-594
Abstract
Sequential recommenders have recently achieved strong gains by modeling the temporal structure of user behavior, yet most systems still rely on shallow item representations that capture co-occurrence statistics rather than the underlying semantics of content. This paper proposes the Semantic Resonance System (SRR), a unified architecture that integrates deep semantic signals from a large language model (LLM) with standard behavioral embeddings for sequential recommendation. SRR uses a domain-adapted Llama 2 13B model, fine-tuned via ParameterEfficient Fine-Tuning (LoRA), to produce high-fidelity semantic item embeddings that are fused with behavioral embeddings through a Dynamic Cross-Attention module. A central component of SRR is the Semantic Resonance Optimization (SRO) loss, which jointly optimizes (i) a Dense All-Action (DAA) loss for high-recall retrieval, (ii) a Binary Cross-Entropy (BCE) loss for calibrated scores, and (iii) a Contrastive Alignment loss $\mathcal{L}_{C A}$ that explicitly aligns semantic and behavioral latent spaces. On the large-scale MovieLens $\mathbf{2 5 M}$ dataset, SRR achieves a $\mathbf{1 6. 4 \%}$ improvement in NDCG@10 over a strong transfer-learning baseline, while also improving diversity, catalog coverage, and cold-start performance. A latency-effectiveness study further shows that SRR can be configured along a smooth Pareto frontier between NDCG@10 and inference cost, supporting deployment under different resource budgets.
Keywords
This publication has 9 references indexed in Scilit:
- Transfer Learning for Efficient Domain Adaptation in Sequential Recommendation Systems2025
- Domain Focused Sequence Model Architecture for Predicting Long Term User Interests2025
- Adaptive Weighted Loss for Sequential Recommendations on Sparse Domains2025
- Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)2022
- PinnerFormer2022
- S3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization2020
- Self-Attentive Sequential Recommendation2018
- Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts2018
- Factorization Machines2010