Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach

By Junjie Zhang, Ruobing Xie, Yupeng Hou, Wayne Xin Zhao, Leyu Lin, Ji-rong Wen. ACM Trans. Inf. Syst., 2023

372 citations recorded by the source corpus.

In the past few decades, recommender systems have attracted much attention in both research and industry communities. Existing recommendation models mainly learn the underlying user preference from historical behavior data (typically in the forms of item IDs), and then estimate the user–item matching relationships for recommendations. Inspired by the recent progress on large language models (LLMs), we develop a different recommendation paradigm, considering recommendation as instruction following by LLMs. The key idea is that the needs of a user can be expressed in natural language descriptions (called instructions), so that LLMs can understand and further execute the instruction for fulfilling the recommendation. For this purpose, we instruction tune the 3B Flan-T5-XL, to better adapt LLMs to recommender systems. We first design a general instruction format for describing the preference, intention, and task form of a user in natural language. Then we manually design 39 instruction templates and automatically generate large amounts of user-personalized instruction data with varying types of preferences and intentions. To demonstrate the effectiveness of our approach, we instantiate the instructions into several widely studied recommendation (or search) tasks, and conduct extensive experiments with real-world datasets. Experiment results show that our approach can outperform several competitive baselines, including the powerful GPT-3.5, on these evaluation tasks. Our approach sheds light on developing user-friendly recommender systems, in which users can freely communicate with the system and obtain accurate recommendations via natural language instructions.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/0383e049e98c9eedbc61be728d4ef037300bbedf

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Wayne Xin Zhao
2. Ji-rong Wen
3. Yupeng Hou
4. Hongyu Lu
5. Bowen Zheng
6. Yu Chen
7. Ruobing Xie
8. Junjie Zhang

In Information Systems

1. Wayne Xin Zhao
2. Yupeng Hou
3. Ji-rong Wen
4. Hongyu Lu
5. Bowen Zheng
6. Yu Chen
7. Ruobing Xie
8. Junjie Zhang

Citations in the corpus

• Large Language Models for Information Retrieval: A Survey (2023, neutral): “The term “document” will henceforth refer to any text-based content subject to retrieve, including both long articles and short passages.”
• Recommender Systems in the Era of Large Language Models (LLMs) (2023, positive): “One is the few-shot setting, in which a few demonstrations with contexts and desired completions of the specific downstream tasks are provided along with prompts.”
• LLMRec: Large Language Models with Graph Augmentation for Recommendation (2023, background): “Future directions for investigation include integrating causal inference into side information debiasing and exploring counterfactual factors for context-aware user preference.”
• Representation Learning with Large Language Models for Recommendation (2023, background): “These limitations can be attributed to three key factors: i) The hallucination issue of LLMs, where they may suggest recommended items that are not included in the candidate set; ii) The lack of a comprehensive global text-based collaborative relationship input due to the token limit of LLMs; iii)…”
• A survey on large language models for recommendation (2023, neutral): “Pre-trained language models have exhibited fairness issues related to sensitive attributes [Zhang et al. , 2023a], which are influenced by the training data or the demographics of the individuals involved in certain task annotations [ Ferrara, 2023 ] .”
• Large Language Models are Zero-Shot Rankers for Recommender Systems (2023, background): “Indeed, there are some preliminary attempts that employ LLMs for solving recommendation tasks [9, 29, 30, 5, 21, 34].”
• Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation (2023, methodology): “…IV-C), these tuning tasks are useful in adapting LLMs to recommender systems. b) Item prediction based on user intention: Drawing inspiration from [19], a recommender system in real life should possess the ability to understand the actual intentions of users and provide high-quality…”