LLM-RecG: A Semantic Bias-Aware Framework for Zero-Shot Sequential Recommendation
This addresses the challenge of making recommendations in unseen domains without training data, which is crucial for sparse data environments, but it is incremental as it builds on existing LLM-based methods.
The paper tackles the problem of domain semantic bias in zero-shot cross-domain sequential recommendation, which reduces generalization across domains, and proposes a framework that improves cross-domain alignment at item and sequential levels, achieving state-of-the-art performance with up to 12.7% improvement in NDCG@10.
Zero-shot cross-domain sequential recommendation (ZCDSR) enables predictions in unseen domains without additional training or fine-tuning, addressing the limitations of traditional models in sparse data environments. Recent advancements in large language models (LLMs) have significantly enhanced ZCDSR by facilitating cross-domain knowledge transfer through rich, pretrained representations. Despite this progress, domain semantic bias -- arising from differences in vocabulary and content focus between domains -- remains a persistent challenge, leading to misaligned item embeddings and reduced generalization across domains. To address this, we propose a novel semantic bias-aware framework that enhances LLM-based ZCDSR by improving cross-domain alignment at both the item and sequential levels. At the item level, we introduce a generalization loss that aligns the embeddings of items across domains (inter-domain compactness), while preserving the unique characteristics of each item within its own domain (intra-domain diversity). This ensures that item embeddings can be transferred effectively between domains without collapsing into overly generic or uniform representations. At the sequential level, we develop a method to transfer user behavioral patterns by clustering source domain user sequences and applying attention-based aggregation during target domain inference. We dynamically adapt user embeddings to unseen domains, enabling effective zero-shot recommendations without requiring target-domain interactions...