Multi-LLM Token Filtering and Routing for Sequential Recommendation

TL;DR

This paper introduces MLTFR, a framework that filters and combines token embeddings from multiple LLMs to improve sequential recommendation without relying on textual input or model modification.

Contribution

MLTFR is a novel method that uses interaction-guided token filtering and a Mixture-of-Experts to leverage multiple LLMs for stable, corpus-free sequential recommendation.

Findings

MLTFR outperforms state-of-the-art baselines in experiments.

Filtering relevant tokens improves recommendation stability.

Combining multiple LLMs enhances semantic coverage and accuracy.

Abstract

Large language models (LLMs) have recently shown promise in recommendation by providing rich semantic knowledge. While most existing approaches rely on external textual corpora to align LLMs with recommender systems, we revisit a more fundamental yet underexplored question: Can recommendation benefit from LLM token embeddings alone without textual input? Through a systematic empirical study, we show that directly injecting token embeddings from a single LLM into sequential recommenders leads to unstable or limited gains, due to semantic misalignment, insufficient task adaptation, and the restricted coverage of individual LLMs. To address these challenges, we propose MLTFR, a Multi-LLM Token Filtering and Routing framework for corpus-free sequential recommendation. MLTFR follows an interaction-guided LLM knowledge integration paradigm, where task-relevant token embeddings are selected via user-guided token filtering to suppress noisy and irrelevant vocabulary signals. To overcome the limitations of single-LLM representations, MLTFR integrates multiple LLM token spaces through a Mixture-of-Experts architecture, with a Fisher-weighted semantic consensus expert to balance heterogeneous experts and prevent domination during training. By jointly filtering informative tokens and aggregating complementary semantic knowledge across multiple LLMs, MLTFR enables stable and effective utilization of LLM token embeddings without textual inputs or backbone modification. Extensive experiments demonstrate that MLTFR consistently outperforms state-of-the-art sequential recommendation baselines and existing alignment methods. Our code is available at: https://github.com/ccwwhhh/MLTFR.