Next-Generation-LLM-based-Recommender-Systems-Survey

Next-Generation-LLM-based-Recommender-Systems-Survey

The official GitHub page for the survey paper "Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond". And this paper is under review.

Stars: 84

Visit
screenshot

The Next-Generation LLM-based Recommender Systems Survey is a comprehensive overview of the latest advancements in recommender systems leveraging Large Language Models (LLMs). The survey covers various paradigms, approaches, and applications of LLMs in recommendation tasks, including generative and non-generative models, multimodal recommendations, personalized explanations, and industrial deployment. It discusses the comparison with existing surveys, different paradigms, and specific works in the field. The survey also addresses challenges and future directions in the domain of LLM-based recommender systems.

README:

Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond

The official GitHub page for the survey paper "Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond".

Introduction

Alt text

The comparison between this work and existing surveys

Paper Non-Gen. RS Gen. RS Scen. Aca. Ind. Pipeline Highlights
'A survey on large language models for recommendation' ✅ ✅ common (all kinds) ✅ (1) Discriminative LLM4REC (2) Generative LLM4REC Modeling Paradigms: (i) LLM Embeddings + RS (ii) LLM Tokens + RS (iii) LLM as RS focuses on expanding the capacity of language models
'How Can Recommender Systems Benefit from Large Language Models: A Survey' ✅ common (all kinds) ✅ (1) Where to adapt to LLM (2) How to adapt to LLM from the angle of the whole pipeline in industrial recommender systems
'A Survey on Large Language Models for Personalized and Explainable Recommendations' ✅ personalized and explainable RecSys ✅ (1) Explanation Generating for Recommendation focuses on utilizing LLMs for personalized explanation generating task
'Recommender systems in the era of large language models (llms)' ✅ common (all kinds) ✅ (1) Pre-training (2) Fine-tuning (3) Prompting comprehensively reviews such domain-specific techniques for adapting LLMs to recommendations
'A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)' ✅ (1) interaction-driven (2) text-driven (3) multimodal ✅ (1) Generative Models for Interaction-Driven Recommendation (2) Large Language Models in Recommendation (3) Generative Multimodal Recommendation Systems aims to connect the key advancements in RS using Generative Models (Gen-RecSys)
Multimodal Pretraining, Adaptation, and Generation for Recommendation: A Survey ✅ multimodal recommendation ✅ (1) Multimodal Pretraining for Recommendation (2) Multimodal Adaption for Recommendation (3) Multimodal Generation for Recommendation seeks to provide a comprehensive exploration of the latest advancements and future trajectories in multimodal pretraining, adaptation, and generation techniques, as well as their applications to recommender systems
'Large language models for generative recommendation: A survey and visionary discussions' ✅ common (all kinds) ✅ (1) ID Creation Methods (2) How to Do Generative Recommendation reviews the recent progress of LLM-based generative recommendation and provides a general formulation for each generative recommendation task according to relevant research
Ours ✅ ✅ common (all kinds) ✅ ✅ (1) Representing and Understanding (2) Scheming and Utilizing (3) Industrial Deploying (1) reviews existing works from the perspective of recommender system community (2) clearly discuss the gap from academic research to industrial application

(Gen.: Generative, RS: Recommendation System, Scen.: Scenarios, Aca.: Academic, Ind.: Industrial)

Structure

Alt text

Pipeline

Alt text

Different paradigm

Alt text

LLM-using

Alt text

Representing and Understanding

Representing

Uni-Modality

  1. LLaRA: Large Language-Recommendation Assistant
  2. DRDT: Dynamic Reflection with Divergent Thinking for LLM-based Sequential Recommendation
  3. Modeling User Viewing Flow using Large Language Models for Article Recommendation
  4. Harnessing Large Language Models for Text-Rich Sequential Recommendation
  5. FineRec: Exploring Fine-grained Sequential Recommendation
  6. Enhancing Sequential Recommendation via LLM-based Semantic Embedding Learning
  7. A Multi-facet Paradigm to Bridge Large Language Model and Recommendation
  8. Understanding Before Recommendation: Semantic Aspect-Aware Review Exploitation via Large Language Models
  9. Representation Learning with Large Language Models for Recommendation
  10. LLM-Enhanced User-Item Interactions: Leveraging Edge Information for Optimized Recommendations
  11. GenRec: Large Language Model for Generative Recommendation
  12. IDGenRec: LLM-RecSys Alignment with Textual ID Learning
  13. Collaborative Large Language Model for Recommender Systems
  14. Multiple Key-value Strategy in Recommendation Systems Incorporating Large Language Model

Multi-Modality

  1. LLMRec: Large Language Models with Graph Augmentation for Recommendation
  2. InteraRec: Interactive Recommendations Using Multimodal Large Language Models
  3. Zero-Shot Recommendations with Pre-Trained Large Language Models for Multimodal Nudging
  4. Large Language Models for Next Point-of-Interest Recommendation
  5. Heterogeneous Knowledge Fusion: A Novel Approach for Personalized Recommendation via LLM
  6. MMREC: LLM Based Multi-Modal Recommender System
  7. Harnessing Multimodal Large Language Models for Multimodal Sequential Recommendation
  8. X-Reflect: Cross-Reflection Prompting for Multimodal Recommendation

Understanding

Pre-Recommendation Explanations

  1. Understanding Before Recommendation: Semantic Aspect-Aware Review Exploitation via Large Language Models
  2. Learning Structure and Knowledge Aware Representation with Large Language Models for Concept Recommendation
  3. LLM-Guided Multi-View Hypergraph Learning for Human-Centric Explainable Recommendation
  4. RDRec: Rationale Distillation for LLM-based Recommendation
  5. User-Centric Conversational Recommendation: Adapting the Need of User with Large Language Models
  6. LLMRG: Improving Recommendations through Large Language Model Reasoning Graphs

Post-Recommendation Explanations

  1. Unlocking the Potential of Large Language Models for Explainable Recommendations
  2. Fine-Tuning Large Language Model Based Explainable Recommendation with Explainable Quality Reward
  3. LLM4Vis: Explainable Visualization Recommendation using ChatGPT
  4. Navigating User Experience of ChatGPT-based Conversational Recommender Systems: The Effects of Prompt Guidance and Recommendation Domain
  5. DRE: Generating Recommendation Explanations by Aligning Large Language Models at Data-level
  6. Uncertainty-Aware Explainable Recommendation with Large Language Models
  7. Where to Move Next: Zero-shot Generalization of LLMs for Next POI Recommendation
  8. Leveraging ChatGPT for Automated Human-centered Explanations in Recommender Systems
  9. Logic-Scaffolding: Personalized Aspect-Instructed Recommendation Explanation Generation using LLMs
  10. Leveraging Large Language Models in Conversational Recommender Systems
  11. Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System
  12. Leveraging Large Language Models for Recommendation and Explanation
  13. GPT as a Baseline for Recommendation Explanation Texts
  14. Supporting Student Decisions on Learning Recommendations: An LLM-Based Chatbot with Knowledge Graph Contextualization for Conversational Explainability and Mentoring
  15. Knowledge Graphs as Context Sources for LLM-Based Explanations of Learning Recommendations
  16. BookGPT: A General Framework for Book Recommendation Empowered by Large Language Model
  17. LLMRec: Benchmarking Large Language Models on Recommendation Task
  18. PAP-REC: Personalized Automatic Prompt for Recommendation Language Model
  19. RecMind: Large Language Model Powered Agent For Recommendation
  20. Prompt Distillation for Efficient LLM-based Recommendation

Scheming and Utilizing

Non-Generative LLM-based Approaches

LLM Retraing

Naive Fine-Tuning
  1. Rethinking Large Language Model Architectures for Sequential Recommendations
  2. LLMRec: Benchmarking Large Language Models on Recommendation Task
  3. Improving Sequential Recommendations with LLMs
  4. An Unified Search and Recommendation Foundation Model for Cold-Start Scenario
  5. Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations
  6. Leveraging Large Language Models for Sequential Recommendation
  7. A Large Language Model Enhanced Conversational Recommender System
  8. Exploring Fine-tuning ChatGPT for News Recommendation
  9. Aligning Large Language Models with Recommendation Knowledge
  10. Conversational Recommender System and Large Language Model Are Made for Each Other in E-commerce Pre-sales Dialogue
  11. Data-Efficient Fine-Tuning for LLM-based Recommendation
  12. Large Language Model with Graph Convolution for Recommendation
  13. A Bi-Step Grounding Paradigm for Large Language Models in Recommendation Systems
  14. Learning Structure and Knowledge Aware Representation with Large Language Models for Concept Recommendation
  15. LoRec: Large Language Model for Robust Sequential Recommendation against Poisoning Attacks
  16. To Recommend or Not: Recommendability Identification in Conversations with Pre-trained Language Models
  17. Large Language Models for Next Point-of-Interest Recommendation
  18. Leveraging large language models in conversational recommender systems
  19. Fine-Tuning Large Language Model Based Explainable Recommendation with Explainable Quality Reward
  20. Enhancing Recommendation Diversity by Re-ranking with Large Language Models
  21. NoteLLM: A Retrievable Large Language Model for Note Recommendation
  22. Harnessing Large Language Models for Text-Rich Sequential Recommendation
  23. LLM4DSR: Leveraing Large Language Model for Denoising Sequential Recommendation
  24. Beyond Inter-Item Relations: Dynamic Adaptive Mixture-of-Experts for LLM-Based Sequential Recommendation
  25. Improving Sequential Recommendations with LLMs
Instruction Tuning
  1. A Multi-facet Paradigm to Bridge Large Language Model and Recommendation
  2. Heterogeneous Knowledge Fusion: A Novel Approach for Personalized Recommendation via LLM
  3. Exploring Large Language Model for Graph Data Understanding in Online Job Recommendations
  4. Item-side Fairness of Large Language Model-based Recommendation System
  5. Integrating Large Language Models into Recommendation via Mutual Augmentation and Adaptive Aggregation
  6. RecRanker: Instruction Tuning Large Language Model as Ranker for Top-k Recommendation
  7. E4SRec: An Elegant Effective Efficient Extensible Solution of Large Language Models for Sequential Recommendation
  8. LLaRA: Large Language-Recommendation Assistant
  9. Unlocking the Potential of Large Language Models for Explainable Recommendations
  10. LlamaRec: Two-Stage Recommendation using Large Language Models for Ranking
  11. Review-driven Personalized Preference Reasoning with Large Language Models for Recommendation
Low-Rank Adapataion (LoRA)
  1. ONCE: Boosting Content-based Recommendation with Both Open- and Closed-source Large Language Models
  2. Breaking the Length Barrier: LLM-Enhanced CTR Prediction in Long Textual User Behaviors
  3. TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation
  4. Harnessing Large Language Models for Text-Rich Sequential Recommendation
  5. E4SRec: An Elegant Effective Efficient Extensible Solution of Large Language Models for Sequential Recommendation
  6. Enhancing Content-based Recommendation via Large Language Model
  7. Large Language Model Distilling Medication Recommendation Model
  8. LLaRA: Large Language-Recommendation Assistant
  9. Exact and Efficient Unlearning for Large Language Model-based Recommendation
  10. Towards Efficient and Effective Unlearning of Large Language Models for Recommendation
  11. LLM-based Federated Recommendation
  12. Aligning Large Language Models for Controllable Recommendations
  13. Lifelong Personalized Low-Rank Adaptation of Large Language Models for Recommendation
  14. Harnessing Multimodal Large Language Models for Multimodal Sequential Recommendation
  15. GANPrompt: Enhancing Robustness in LLM-Based Recommendations with GAN-Enhanced Diversity Prompts
  16. DELRec: Distilling Sequential Pattern to Enhance LLM-based Recommendation
  17. CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendation

LLM Reusing

Direct Utilizing
  1. Knowledge Plugins: Enhancing Large Language Models for Domain-Specific Recommendations
  2. DRDT: Dynamic Reflection with Divergent Thinking for LLM-based Sequential Recommendation
  3. Zero-Shot Next-Item Recommendation using Large Pretrained Language Models
  4. Zero-Shot Recommendations with Pre-Trained Large Language Models for Multimodal Nudging
  5. Large Language Models are Competitive Near Cold-start Recommenders for Language- and Item-based Preferences
  6. Large Language Model Augmented Narrative Driven Recommendations
  7. ChatGPT for Conversational Recommendation: Refining Recommendations by Reprompting with Feedback
  8. Federated Recommendation via Hybrid Retrieval Augmented Generation
  9. Re2LLM: Reflective Reinforcement Large Language Model for Session-based Recommendation
  10. RecMind: Large Language Model Powered Agent For Recommendation
  11. Reindex-Then-Adapt: Improving Large Language Models for Conversational Recommendation
  12. Improve Temporal Awareness of LLMs for Sequential Recommendation
  13. Tired of Plugins? Large Language Models Can Be End-To-End Recommenders
  14. Where to Move Next: Zero-shot Generalization of LLMs for Next POI Recommendation
  15. Large Language Models are Zero-Shot Rankers for Recommender Systems
  16. InteraRec: Interactive Recommendations Using Multimodal Large Language Models
  17. Large Language Models are Learnable Planners for Long-Term Recommendation
  18. Logic-Scaffolding: Personalized Aspect-Instructed Recommendation Explanation Generation using LLMs
  19. ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation
  20. RDRec: Rationale Distillation for LLM-based Recommendation
  21. LLM-Guided Multi-View Hypergraph Learning for Human-Centric Explainable Recommendation
  22. Large Language Model Interaction Simulator for Cold-Start Item Recommendation
  23. LLMRec: Large Language Models with Graph Augmentation for Recommendation
  24. LKPNR: LLM and KG for Personalized News Recommendation Framework
  25. LLM4Vis: Explainable Visualization Recommendation using ChatGPT
  26. LLMRG: Improving Recommendations through Large Language Model Reasoning Graphs
  27. Large Language Models for Intent-Driven Session Recommendations
  28. Understanding Before Recommendation: Semantic Aspect-Aware Review Exploitation via Large Language Models
  29. Leveraging Large Language Models (LLMs) to Empower Training-Free Dataset Condensation for Content-Based Recommendation
  30. CoRAL: Collaborative Retrieval-Augmented Large Language Models Improve Long-tail Recommendation
  31. Common Sense Enhanced Knowledge-based Recommendation with Large Language Model
  32. DynLLM: When Large Language Models Meet Dynamic Graph Recommendation
  33. FineRec: Exploring Fine-grained Sequential Recommendation
  34. LLM4SBR: A Lightweight and Effective Framework for Integrating Large Language Models in Session-based Recommendation
  35. Breaking the Barrier: Utilizing Large Language Models for Industrial Recommendation Systems through an Inferential Knowledge Graph
  36. Sequential Recommendation with Latent Relations based on Large Language Model
  37. News Recommendation with Category Description by a Large Language Model
  38. PAP-REC: Personalized Automatic Prompt for Recommendation Language Model
  39. Large Language Models as Data Augmenters for Cold-Start Item Recommendation
  40. MMREC: LLM Based Multi-Modal Recommender System
  41. DaRec: A Disentangled Alignment Framework for Large Language Model and Recommender System
  42. X-Reflect: Cross-Reflection Prompting for Multimodal Recommendation
  43. LLM4MSR: An LLM-Enhanced Paradigm for Multi-Scenario Recommendation
  44. LLM-Based Aspect Augmentations for Recommendation Systems
  45. Towards Open-World Recommendation with Knowledge Augmentation from Large Language Models
  46. LLM-Rec: Personalized Recommendation via Prompting Large Language Models
Prompt Tuning
  1. PMG: Personalized Multimodal Generation with Large Language Models
  2. Language-Based User Profiles for Recommendation
  3. Prompt Tuning Large Language Models on Personalized Aspect Extraction for Recommendations
  4. RecPrompt: A Prompt Tuning Framework for News Recommendation Using Large Language Models
In-Context Learning (ICL)
  1. Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System
  2. DRE: Generating Recommendation Explanations by Aligning Large Language Models at Data-level
  3. Efficient and Responsible Adaptation of Large Language Models for Robust Top-k Recommendations
  4. Uncovering ChatGPT’s Capabilities in Recommender Systems
  5. New Community Cold-Start Recommendation: A Novel Large Language Model-based Method
  6. LANE: Logic Alignment of Non-tuning Large Language Models and Online Recommendation Systems for Explainable Reason Generation

Generative LLM-based Approaches

LLM Retraing

Naive Fine-Tuning
  1. GPT4Rec: A Generative Framework for Personalized Recommendation and User Interests Interpretation
  2. LLM-Enhanced User-Item Interactions: Leveraging Edge Information for Optimized Recommendations
  3. RecGPT: Generative Personalized Prompts for Sequential Recommendation via ChatGPT Training Paradigm
  4. RecGPT: Generative Pre-training for Text-based Recommendation
  5. IDGenRec: LLM-RecSys Alignment with Textual ID Learning
  6. Collaborative large language model for recommender systems
  7. CALRec: Contrastive Alignment of Generative LLMs For Sequential Recommendation
Instruction Tuning
  1. Multiple Key-Value Strategy in Recommendation Systems Incorporating Large Language Model
Low-Rank Adaptation (LoRA)
  1. Genrec: Large Language Model for Generative Recommendation

LLM Reusing

Direct Utilizing
  1. How to Index Item IDs for Recommendation Foundation Models
  2. Supporting Student Decisions on Learning Recommendations: An LLM-based Chatbot with Knowledge Graph Contextualization for Conversational Explainability and Mentoring
  3. Large Language Models as Zero-Shot Conversational Recommenders
  4. Bookgpt: A General Framework for Book Recommendation Empowered by Large Language Model
  5. ONCE: Boosting Content-based Recommendation with Both Open- and Closed-source Large Language Models
Prompt Tuning
  1. PMG: Personalized Multimodal Generation with Large Language Models

Components or Strategies for Generative Recommendation

  1. Learnable Tokenizer for LLM-based Generative Recommendation

The existing LLM-based works for generative recommendations

Model/Paper Task/Domain Data Modality Main Techniques Source Code
'Multiple Key-value Strategy in Recommendation Systems Incorporating Large Language Model' sequential recommendation multiple key-value data pre-train, instruction tuning ~
'Large language models as zero-shot conversational recommenders' zero-shot conversational recommendation text (conversational recommendation dataset) prompt https://github.com/AaronHeee/LLMs-as-Zero-Shot-Conversational-RecSys
'Bookgpt: A general framework for book recommendation empowered by large language model' book recommendation interaction, text prompt https://github.com/zhiyulee-RUC/bookgpt
'How to index item ids for recommendation foundation models' sequential recommendation interaction, text item ID indexing https://github.com/Wenyueh/LLM-RecSys-ID
'Supporting student decisions on learning recommendations: An llm-based chatbot with knowledge graph contextualization for conversational explainability and mentoring' learning recommendation graph data, text ~ ~
'GPT4Rec: A generative framework for personalized recommendation and user interests interpretation' next-item prediction interaction, item title prompt, pre-train, fine-tune ~
'LLM-Enhanced User-Item Interactions: Leveraging Edge Information for Optimized Recommendations' item recommendation interaction prompt, pre-train, fine-tune https://github.com/anord-wang/LLM4REC.git
'RecGPT: Generative Personalized Prompts for Sequential Recommendation via ChatGPT Training Paradigm' sequential recommendation sequences of words prompt, pre-train, fine-tune ~
'RecGPT: Generative Pre-training for Text-based Recommendation' rating prediction, sequential recommendation text pre-train, fine-tune https://github.com/VinAIResearch/RecGPT
'Genrec: Large language model for generative recommendation' movie recommendation interaction, textual-information prompt, pre-train, fine-tune https://github.com/rutgerswiselab/GenRec
'IDGenRec: LLM-RecSys Alignment with Textual ID Learning' sequential recommendation, zero-shot recommendation interaction, text natural language generation https://github.com/agiresearch/IDGenRec
'Collaborative large language model for recommender systems' item recommendation interaction, text prompt, pre-train, fine-tune https://github.com/yaochenzhu/llm4rec
'PMG: Personalized Multimodal Generation with Large Language Models' personalized multimodal generation text, image, audio, etc prompt, pre-train, Prompt Tuning (P-Tuning V2) https://github.com/mindspore-lab/models/tree/master/research/huawei-noah/PMG
'CALRec: Contrastive Alignment of Generative LLMs For Sequential Recommendation' sequential recommendation interaction, text pre-train, fine-tune, contrastive learning ~
'Once: Boosting content-based recommendation with both open-and closed-source large language models' content-based recommendation (news recommendation, book recommendation) interaction, text prompt https://github.com/Jyonn/ONCE

Industrial Deploying

Large-Scale Industrial Scenarios

  1. Breaking the Barrier: Utilizing Large Language Models for Industrial Recommendation Systems through an Inferential Knowledge Graph
  2. A Large Language Model Enhanced Sequential Recommender for Joint Video and Comment Recommendation
  3. RecGPT: Generative Personalized Prompts for Sequential Recommendation via ChatGPT Training Paradigm
  4. Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Application
  5. Enhancing Sequential Recommendation via LLM-based Semantic Embedding Learning
  6. Actions speak louder than words: Trillion-parameter sequential transducers for generative recommendations
  7. Breaking the length barrier: LLM-Enhanced CTR Prediction in Long Textual User Behaviors
  8. LLM4SBR: A Lightweight and Effective Framework for Integrating Large Language Models in Session-based Recommendation

Acceleration

  1. A Decoding Acceleration Framework for Industrial Deployable LLM-based Recommender Systems

Cold Start

  1. An Unified Search and Recommendation Foundation Model for Cold-Start Scenario
  2. Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Application
  3. Breaking the Barrier: Utilizing Large Language Models for Industrial Recommendation Systems through an Inferential Knowledge Graph

Dynamic Update

  1. DynLLM: When Large Language Models Meet Dynamic Graph Recommendation
  2. Actions speak louder than words: Trillion-parameter sequential transducers for generative recommendations
  3. COSMO: A large-scale e-commerce common sense knowledge generation and serving system at Amazon

Adapting to Business Customization Requirements

  1. Modeling User Viewing Flow using Large Language Models for Article Recommendation
  2. Ad Recommendation in a Collapsed and Entangled World
  3. NoteLLM: A Retrievable Large Language Model for Note Recommendation
  4. Beyond Labels: Leveraging Deep Learning and LLMs for Content Metadata
  5. TRAWL: External Knowledge-Enhanced Recommendation with LLM Assistance
  6. Heterogeneous Knowledge Fusion: A Novel Approach for Personalized Recommendation via LLM
  7. COSMO: A large-scale e-commerce common sense knowledge generation and serving system at Amazon

The existing LLM-based works which could be deployed in industry

Model/Paper Company Task/Domain Highlights
LLM-KERec, 'Breaking the Barrier: Utilizing Large Language Models for Industrial Recommendation Systems through an Inferential Knowledge Graph' Ant Group E-commerce Recommendation Constructs a complementary knowledge graph by LLMs
LSVCR, 'A Large Language Model Enhanced Sequential Recommender for Joint Video and Comment Recommendation' KuaiShou Video Recommendation Sequential recommendation model and supplemental LLM recommender
RecGPT, 'RecGPT: Generative Personalized Prompts for Sequential Recommendation via ChatGPT Training Paradigm' KuaiShou Sequential Recommendation Models user behavior sequences using personalized prompts with ChatGPT.
SAID, 'Enhancing sequential recommendation via llm-based semantic embedding learning' Ant Group Sequential Recommendation Explicitly learns Semantically Aligned item ID embeddings based on texts by utilizing LLMs.
BAHE, 'Breaking the length barrier: Llm-enhanced CTR prediction in long textual user behaviors' Ant Group CTR Prediction Uses LLM's shallow layers for user behavior embeddings and deep layers for behavior interactions.
'LLM4SBR: A Lightweight and Effective Framework for Integrating Large Language Models in Session-based Recommendation' HuaWei Session-based Recommendation In short sequence data, LLM can infer preferences directly leveraging its language understanding capability without fine-tuning
DARE, 'A Decoding Acceleration Framework for Industrial Deployable LLM-based Recommender Systems' HuaWei CTR prediction Identifies the issue of inference efficiency during deploying LLM-based recommendations and introduces speculative decoding to accelerate recommendation knowledge generation.
'An Unified Search and Recommendation Foundation Model for Cold-Start Scenario' Ant Group Multi-domain Recommendation LLM is applied to the S&R multi-domain foundation model to extract domain-invariant text features.
LEARN, 'Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Application' Kuaishou Sequential Recommendation Integrates the open-world knowledge encapsulated in LLMs into RS.
'DynLLM: When Large Language Models Meet Dynamic Graph Recommendation' Alibaba E-commerce Recommendations Generates user profiles based on textual historical purchase records and obtaining users' embeddings by LLM.
HSTU, 'Actions speak louder than words: Trillion-parameter sequential transducers for generative recommendations' Meta Generating user action sequence Explores the scaling laws of RS; Optimising model architecture to accelerate inference.
COSMO, 'COSMO: A large-scale e-commerce common sense knowledge generation and serving system at Amazon' Amazon Semantic relevance and session-based recommendation Is the first industry-scale knowledge system that adopts LLM to construct high-quality knowledge graphs and serve online applications
SINGLE, 'Modeling User Viewing Flow using Large Language Models for Article Recommendation' Taobao, Alibaba Article Recommendation Summarises long articles and the user constant preference from view history by gpt-3.5-turbo or ChatGLM-6B.
'Ad Recommendation in a Collapsed and Entangled World' Tencent Ad Recommendation Obtains user or items embeddings by LLM.
NoteLLM, 'NoteLLM: A Retrievable Large Language Model for Note Recommendation' xiaohongshu.com Item-to-item Note Recommendation Obtains article embeddings and generate hashtags/categories information by LLaMA-2.
Genre Spectrum, 'Beyond Labels: Leveraging Deep Learning and LLMs for Content Metadata' tubi.tv Movie & TV series Recommendation Obtains content metadata embeddings by LLM.
TRAWL, 'TRAWL: External Knowledge-Enhanced Recommendation with LLM Assistance' WeChat, Tencent Article Recommendation Uses Qwen1.5-7B extract knowledge from articles.
HKFR, 'Heterogeneous Knowledge Fusion: A Novel Approach for Personalized Recommendation via LLM' Meituan Catering Recommendation Uses heterogeneous knowledge fusion for recommendations.

Challenges

Alt text

Alt text

For Tasks:

Click tags to check more tools for each tasks
generate personalized recommendations improve recommendation diversity explain recommendation results deploy recommender systems enhance sequential recommendations

For Jobs:

data scientist machine learning engineer ai researcher recommendation system developer data analyst

Alternative AI tools for Next-Generation-LLM-based-Recommender-Systems-Survey

Similar Open Source Tools

Next-Generation-LLM-based-Recommender-Systems-Survey Screenshot
Next-Generation-LLM-based-Recommender-Systems-Survey

The Next-Generation LLM-based Recommender Systems Survey is a comprehensive overview of the latest advancements in recommender systems leveraging Large Language Models (LLMs). The survey covers various paradigms, approaches, and applications of LLMs in recommendation tasks, including generative and non-generative models, multimodal recommendations, personalized explanations, and industrial deployment. It discusses the comparison with existing surveys, different paradigms, and specific works in the field. The survey also addresses challenges and future directions in the domain of LLM-based recommender systems.

github
: 84
LLMSys-PaperList Screenshot
LLMSys-PaperList

This repository provides a comprehensive list of academic papers, articles, tutorials, slides, and projects related to Large Language Model (LLM) systems. It covers various aspects of LLM research, including pre-training, serving, system efficiency optimization, multi-model systems, image generation systems, LLM applications in systems, ML systems, survey papers, LLM benchmarks and leaderboards, and other relevant resources. The repository is regularly updated to include the latest developments in this rapidly evolving field, making it a valuable resource for researchers, practitioners, and anyone interested in staying abreast of the advancements in LLM technology.

github
: 591
Embodied-AI-Guide Screenshot
Embodied-AI-Guide

Embodied-AI-Guide is a comprehensive guide for beginners to understand Embodied AI, focusing on the path of entry and useful information in the field. It covers topics such as Reinforcement Learning, Imitation Learning, Large Language Model for Robotics, 3D Vision, Control, Benchmarks, and provides resources for building cognitive understanding. The repository aims to help newcomers quickly establish knowledge in the field of Embodied AI.

github
: 98
GIMP-ML Screenshot
GIMP-ML

A.I. for GNU Image Manipulation Program (GIMP-ML) is a repository that provides Python plugins for using computer vision models in GIMP. The code base and models are continuously updated to support newer and more stable functionality. Users can edit images with text, outpaint images, and generate images from text using models like Dalle 2 and Dalle 3. The repository encourages citations using a specific bibtex entry and follows the MIT license for GIMP-ML and the original models.

github
: 1.4k
LLMs4TS Screenshot
LLMs4TS

LLMs4TS is a repository focused on the application of cutting-edge AI technologies for time-series analysis. It covers advanced topics such as self-supervised learning, Graph Neural Networks for Time Series, Large Language Models for Time Series, Diffusion models, Mixture-of-Experts architectures, and Mamba models. The resources in this repository span various domains like healthcare, finance, and traffic, offering tutorials, courses, and workshops from prestigious conferences. Whether you're a professional, data scientist, or researcher, the tools and techniques in this repository can enhance your time-series data analysis capabilities.

github
: 66
litgpt Screenshot
litgpt

LitGPT is a command-line tool designed to easily finetune, pretrain, evaluate, and deploy 20+ LLMs **on your own data**. It features highly-optimized training recipes for the world's most powerful open-source large-language-models (LLMs).

github
: 10.3k
recommenders Screenshot
recommenders

Recommenders is a project under the Linux Foundation of AI and Data that assists researchers, developers, and enthusiasts in prototyping, experimenting with, and bringing to production a range of classic and state-of-the-art recommendation systems. The repository contains examples and best practices for building recommendation systems, provided as Jupyter notebooks. It covers tasks such as preparing data, building models using various recommendation algorithms, evaluating algorithms, tuning hyperparameters, and operationalizing models in a production environment on Azure. The project provides utilities to support common tasks like loading datasets, evaluating model outputs, and splitting training/test data. It includes implementations of state-of-the-art algorithms for self-study and customization in applications.

github
: 18.9k
HuatuoGPT-II Screenshot
HuatuoGPT-II

HuatuoGPT2 is an innovative domain-adapted medical large language model that excels in medical knowledge and dialogue proficiency. It showcases state-of-the-art performance in various medical benchmarks, surpassing GPT-4 in expert evaluations and fresh medical licensing exams. The open-source release includes HuatuoGPT2 models in 7B, 13B, and 34B versions, training code for one-stage adaptation, partial pre-training and fine-tuning instructions, and evaluation methods for medical response capabilities and professional pharmacist exams. The tool aims to enhance LLM capabilities in the Chinese medical field through open-source principles.

github
: 308
AV-Deepfake1M Screenshot
AV-Deepfake1M

The AV-Deepfake1M repository is the official repository for the paper AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset. It addresses the challenge of detecting and localizing deepfake audio-visual content by proposing a dataset containing video manipulations, audio manipulations, and audio-visual manipulations for over 2K subjects resulting in more than 1M videos. The dataset is crucial for developing next-generation deepfake localization methods.

github
: 71
PIXIU Screenshot
PIXIU

PIXIU is a project designed to support the development, fine-tuning, and evaluation of Large Language Models (LLMs) in the financial domain. It includes components like FinBen, a Financial Language Understanding and Prediction Evaluation Benchmark, FIT, a Financial Instruction Dataset, and FinMA, a Financial Large Language Model. The project provides open resources, multi-task and multi-modal financial data, and diverse financial tasks for training and evaluation. It aims to encourage open research and transparency in the financial NLP field.

github
: 525
dl_model_infer Screenshot
dl_model_infer

This project is a c++ version of the AI reasoning library that supports the reasoning of tensorrt models. It provides accelerated deployment cases of deep learning CV popular models and supports dynamic-batch image processing, inference, decode, and NMS. The project has been updated with various models and provides tutorials for model exports. It also includes a producer-consumer inference model for specific tasks. The project directory includes implementations for model inference applications, backend reasoning classes, post-processing, pre-processing, and target detection and tracking. Speed tests have been conducted on various models, and onnx downloads are available for different models.

github
: 87
inference Screenshot
inference

Xorbits Inference (Xinference) is a powerful and versatile library designed to serve language, speech recognition, and multimodal models. With Xorbits Inference, you can effortlessly deploy and serve your or state-of-the-art built-in models using just a single command. Whether you are a researcher, developer, or data scientist, Xorbits Inference empowers you to unleash the full potential of cutting-edge AI models.

github
: 5.1k
llm-datasets Screenshot
llm-datasets

LLM Datasets is a repository containing high-quality datasets, tools, and concepts for LLM fine-tuning. It provides datasets with characteristics like accuracy, diversity, and complexity to train large language models for various tasks. The repository includes datasets for general-purpose, math & logic, code, conversation & role-play, and agent & function calling domains. It also offers guidance on creating high-quality datasets through data deduplication, data quality assessment, data exploration, and data generation techniques.

github
: 1.5k
LLM-PowerHouse-A-Curated-Guide-for-Large-Language-Models-with-Custom-Training-and-Inferencing Screenshot
LLM-PowerHouse-A-Curated-Guide-for-Large-Language-Models-with-Custom-Training-and-Inferencing

LLM-PowerHouse is a comprehensive and curated guide designed to empower developers, researchers, and enthusiasts to harness the true capabilities of Large Language Models (LLMs) and build intelligent applications that push the boundaries of natural language understanding. This GitHub repository provides in-depth articles, codebase mastery, LLM PlayLab, and resources for cost analysis and network visualization. It covers various aspects of LLMs, including NLP, models, training, evaluation metrics, open LLMs, and more. The repository also includes a collection of code examples and tutorials to help users build and deploy LLM-based applications.

github
: 617
amber-train Screenshot
amber-train

Amber is the first model in the LLM360 family, an initiative for comprehensive and fully open-sourced LLMs. It is a 7B English language model with the LLaMA architecture. The model type is a language model with the same architecture as LLaMA-7B. It is licensed under Apache 2.0. The resources available include training code, data preparation, metrics, and fully processed Amber pretraining data. The model has been trained on various datasets like Arxiv, Book, C4, Refined-Web, StarCoder, StackExchange, and Wikipedia. The hyperparameters include a total of 6.7B parameters, hidden size of 4096, intermediate size of 11008, 32 attention heads, 32 hidden layers, RMSNorm ε of 1e^-6, max sequence length of 2048, and a vocabulary size of 32000.

github
: 136
SLR-FC Screenshot
SLR-FC

This repository provides a comprehensive collection of AI tools and resources to enhance literature reviews. It includes a curated list of AI tools for various tasks, such as identifying research gaps, discovering relevant papers, visualizing paper content, and summarizing text. Additionally, the repository offers materials on generative AI, effective prompts, copywriting, image creation, and showcases of AI capabilities. By leveraging these tools and resources, researchers can streamline their literature review process, gain deeper insights from scholarly literature, and improve the quality of their research outputs.

github
: 110

For similar tasks

Next-Generation-LLM-based-Recommender-Systems-Survey Screenshot
Next-Generation-LLM-based-Recommender-Systems-Survey

The Next-Generation LLM-based Recommender Systems Survey is a comprehensive overview of the latest advancements in recommender systems leveraging Large Language Models (LLMs). The survey covers various paradigms, approaches, and applications of LLMs in recommendation tasks, including generative and non-generative models, multimodal recommendations, personalized explanations, and industrial deployment. It discusses the comparison with existing surveys, different paradigms, and specific works in the field. The survey also addresses challenges and future directions in the domain of LLM-based recommender systems.

github
: 84

For similar jobs

weave Screenshot
weave

Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.

github
: 685
LLMStack Screenshot
LLMStack

LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

github
: 1.5k
VisionCraft Screenshot
VisionCraft

The VisionCraft API is a free API for using over 100 different AI models. From images to sound.

github
: 94
kaito Screenshot
kaito

Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.

github
: 405
PyRIT Screenshot
PyRIT

PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.

github
: 1.8k
tabby Screenshot
tabby

Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features: * Self-contained, with no need for a DBMS or cloud service. * OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE). * Supports consumer-grade GPUs.

github
: 21.5k
spear Screenshot
spear

SPEAR (Simulator for Photorealistic Embodied AI Research) is a powerful tool for training embodied agents. It features 300 unique virtual indoor environments with 2,566 unique rooms and 17,234 unique objects that can be manipulated individually. Each environment is designed by a professional artist and features detailed geometry, photorealistic materials, and a unique floor plan and object layout. SPEAR is implemented as Unreal Engine assets and provides an OpenAI Gym interface for interacting with the environments via Python.

github
: 224
Magick Screenshot
Magick

Magick is a groundbreaking visual AIDE (Artificial Intelligence Development Environment) for no-code data pipelines and multimodal agents. Magick can connect to other services and comes with nodes and templates well-suited for intelligent agents, chatbots, complex reasoning systems and realistic characters.

github
: 675