RecMind: Large Language Model Powered Agent For Recommendation
- URL: http://arxiv.org/abs/2308.14296v3
- Date: Wed, 20 Mar 2024 18:13:10 GMT
- Title: RecMind: Large Language Model Powered Agent For Recommendation
- Authors: Yancheng Wang, Ziyan Jiang, Zheng Chen, Fan Yang, Yingxue Zhou, Eunah Cho, Xing Fan, Xiaojiang Huang, Yanbin Lu, Yingzhen Yang,
- Abstract summary: RecMind is an autonomous recommender agent with careful planning for zero-shot personalized recommendations.
Our experiment shows that RecMind outperforms existing zero/few-shot LLM-based recommendation baseline methods in various tasks.
- Score: 16.710558148184205
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: While the recommendation system (RS) has advanced significantly through deep learning, current RS approaches usually train and fine-tune models on task-specific datasets, limiting their generalizability to new recommendation tasks and their ability to leverage external knowledge due to model scale and data size constraints. Thus, we designed an LLM-powered autonomous recommender agent, RecMind, which is capable of leveraging external knowledge, utilizing tools with careful planning to provide zero-shot personalized recommendations. We propose a Self-Inspiring algorithm to improve the planning ability. At each intermediate step, the LLM self-inspires to consider all previously explored states to plan for the next step. This mechanism greatly improves the model's ability to comprehend and utilize historical information in planning for recommendation. We evaluate RecMind's performance in various recommendation scenarios. Our experiment shows that RecMind outperforms existing zero/few-shot LLM-based recommendation baseline methods in various tasks and achieves comparable performance to a fully trained recommendation model P5.
Related papers
- LANE: Logic Alignment of Non-tuning Large Language Models and Online Recommendation Systems for Explainable Reason Generation [15.972926854420619]
Leveraging large language models (LLMs) offers new opportunities for comprehensive recommendation logic generation.
Fine-tuning LLM models for recommendation tasks incurs high computational costs and alignment issues with existing systems.
In this work, our proposed effective strategy LANE aligns LLMs with online recommendation systems without additional LLMs tuning.
arXiv Detail & Related papers (2024-07-03T06:20:31Z) - Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs [59.76268575344119]
We introduce a novel framework for enhancing large language models' (LLMs) planning capabilities by using planning data derived from knowledge graphs (KGs)
LLMs fine-tuned with KG data have improved planning capabilities, better equipping them to handle complex QA tasks that involve retrieval.
arXiv Detail & Related papers (2024-06-20T13:07:38Z) - Large Language Models are Learnable Planners for Long-Term Recommendation [59.167795967630305]
Planning for both immediate and long-term benefits becomes increasingly important in recommendation.
Existing methods apply Reinforcement Learning to learn planning capacity by maximizing cumulative reward for long-term recommendation.
We propose to leverage the remarkable planning capabilities over sparse data of Large Language Models for long-term recommendation.
arXiv Detail & Related papers (2024-02-29T13:49:56Z) - Uncertainty-Aware Explainable Recommendation with Large Language Models [15.229417987212631]
We develop a model that utilizes the ID vectors of user and item inputs as prompts for GPT-2.
We employ a joint training mechanism within a multi-task learning framework to optimize both the recommendation task and explanation task.
Our method achieves 1.59 DIV, 0.57 USR and 0.41 FCR on the Yelp, TripAdvisor and Amazon dataset respectively.
arXiv Detail & Related papers (2024-01-31T14:06:26Z) - LLMRec: Benchmarking Large Language Models on Recommendation Task [54.48899723591296]
The application of Large Language Models (LLMs) in the recommendation domain has not been thoroughly investigated.
We benchmark several popular off-the-shelf LLMs on five recommendation tasks, including rating prediction, sequential recommendation, direct recommendation, explanation generation, and review summarization.
The benchmark results indicate that LLMs displayed only moderate proficiency in accuracy-based tasks such as sequential and direct recommendation.
arXiv Detail & Related papers (2023-08-23T16:32:54Z) - A Survey on Large Language Models for Recommendation [77.91673633328148]
Large Language Models (LLMs) have emerged as powerful tools in the field of Natural Language Processing (NLP)
This survey presents a taxonomy that categorizes these models into two major paradigms, respectively Discriminative LLM for Recommendation (DLLM4Rec) and Generative LLM for Recommendation (GLLM4Rec)
arXiv Detail & Related papers (2023-05-31T13:51:26Z) - Recommendation as Instruction Following: A Large Language Model
Empowered Recommendation Approach [83.62750225073341]
We consider recommendation as instruction following by large language models (LLMs)
We first design a general instruction format for describing the preference, intention, task form and context of a user in natural language.
Then we manually design 39 instruction templates and automatically generate a large amount of user-personalized instruction data.
arXiv Detail & Related papers (2023-05-11T17:39:07Z) - Evaluating model-based planning and planner amortization for continuous
control [79.49319308600228]
We take a hybrid approach, combining model predictive control (MPC) with a learned model and model-free policy learning.
We find that well-tuned model-free agents are strong baselines even for high DoF control problems.
We show that it is possible to distil a model-based planner into a policy that amortizes the planning without any loss of performance.
arXiv Detail & Related papers (2021-10-07T12:00:40Z) - Developing a Recommendation Benchmark for MLPerf Training and Inference [16.471395965484145]
We aim to define an industry-relevant recommendation benchmark for theerferf Training andInference Suites.
The paper synthesizes the desirable modeling strategies for personalized recommendation systems.
We lay out desirable characteristics of recommendation model architectures and data sets.
arXiv Detail & Related papers (2020-03-16T17:13:00Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.