This repository serves as a curated collection of academic papers and resources focused on the application of Large Language Models (LLMs) in recommender systems. It targets researchers and practitioners in the fields of recommender systems and natural language processing, providing a centralized hub for the latest advancements and foundational works in LLM-enhanced recommendations.

How It Works

The project compiles research papers, categorizing them by their approach to integrating LLMs with recommendation tasks. This includes methods like zero-shot recommendations, prompt-tuning, using LLMs for data augmentation, and leveraging LLMs for interpretability or conversational recommendation. The collection highlights the diverse ways LLMs are being adapted to improve recommendation accuracy, personalization, and user experience.

Quick Start & Requirements

This repository is a curated list of papers and does not have a direct installation or execution command. The primary requirement is access to academic literature databases (e.g., arXiv, ACM, WSDM, etc.) to retrieve the cited papers. Links to official surveys and related tutorials are provided within the README for further exploration.

Highlighted Details

• Comprehensive list of 50+ papers published between 2022-2024, covering various LLM integration strategies.
• Includes a dedicated section for related survey papers and tutorials on LLMs for recommendation.
• Provides a list of common datasets used in LLM-based recommendation research, such as Amazon Review, MIND, and MovieLens.
• Features a section on debuggable generative language models supporting Chinese corpus, useful for researchers with specific language needs.

Maintenance & Community

The repository is maintained by WLiK and includes a significant survey paper authored by multiple researchers, indicating collaborative effort. The README encourages citations and updates, suggesting an ongoing community interest.

Licensing & Compatibility

The repository itself is a list of links and references, not software. The licensing of the individual papers would be governed by their respective publishers or venues. Compatibility for commercial use would depend on the licenses of the cited research papers and any associated code repositories.

Limitations & Caveats

This is a curated list of papers and does not provide direct code implementations or pre-trained models. Users must independently find and evaluate the code and models associated with each paper. The "News" section indicates that the list is continuously updated, but the frequency and completeness of updates are not explicitly stated.