Give Users the Wheel: Towards Promptable Recommendation Paradigm

TL;DR

This paper introduces DPR, a flexible framework that enhances sequential recommendation models with promptability, allowing natural language prompts to steer recommendations without sacrificing efficiency or collaborative accuracy.

Contribution

DPR is a novel, model-agnostic approach that integrates prompt-based user intent into traditional recommendation systems through a fusion module, MoE architecture, and staged training.

Findings

DPR outperforms state-of-the-art baselines in prompt-guided recommendation tasks.

DPR maintains competitive performance in standard sequential recommendation scenarios.

The framework effectively aligns semantic prompts with collaborative signals.

Abstract

Conventional sequential recommendation models have achieved remarkable success in mining implicit behavioral patterns. However, these architectures remain structurally blind to explicit user intent: they struggle to adapt when a user's immediate goal (e.g., expressed via a natural language prompt) deviates from their historical habits. While Large Language Models (LLMs) offer the semantic reasoning to interpret such intent, existing integration paradigms force a dilemma: LLM-as-a-recommender paradigm sacrifices the efficiency and collaborative precision of ID-based retrieval, while Reranking methods are inherently bottlenecked by the recall capabilities of the underlying model. In this paper, we propose Decoupled Promptable Sequential Recommendation (DPR), a model-agnostic framework that empowers conventional sequential backbones to natively support Promptable Recommendation, the ability to dynamically steer the retrieval process using natural language without abandoning collaborative signals. DPR modulates the latent user representation directly within the retrieval space. To achieve this, we introduce a Fusion module to align the collaborative and semantic signals, a Mixture-of-Experts (MoE) architecture that disentangles the conflicting gradients from positive and negative steering, and a three-stage training strategy that progressively aligns the semantic space of prompts with the collaborative space. Extensive experiments on real-world datasets demonstrate that DPR significantly outperforms state-of-the-art baselines in prompt-guided tasks while maintaining competitive performance in standard sequential recommendation scenarios.