Avoid Recommending Out-of-Domain Items: Constrained Generative Recommendation with LLMs
This addresses a practical challenge for developers and users of LLM-based recommender systems, though it is incremental as it builds on existing LLM capabilities.
The paper tackles the problem of preventing large language models (LLMs) from recommending out-of-domain items in generative recommender systems, and finds that a constrained generation method (RecLM-cgen) outperforms retrieval-based and existing LLM-based models in accuracy while eliminating such recommendations.
Large Language Models (LLMs) have shown promise for generative recommender systems due to their transformative capabilities in user interaction. However, ensuring they do not recommend out-of-domain (OOD) items remains a challenge. We study two distinct methods to address this issue: RecLM-ret, a retrieval-based method, and RecLM-cgen, a constrained generation method. Both methods integrate seamlessly with existing LLMs to ensure in-domain recommendations. Comprehensive experiments on three recommendation datasets demonstrate that RecLM-cgen consistently outperforms RecLM-ret and existing LLM-based recommender models in accuracy while eliminating OOD recommendations, making it the preferred method for adoption. Additionally, RecLM-cgen maintains strong generalist capabilities and is a lightweight plug-and-play module for easy integration into LLMs, offering valuable practical benefits for the community. Source code is available at https://github.com/microsoft/RecAI