AiPaper

Papers

Sign in to view your remaining parses.
Tag Filter
LLM-based Recommendation Systems
Large Language Models meet Collaborative Filtering: An Efficient All-round LLM-based Recommender System
Published:4/17/2024
LLM-based Recommendation SystemsCollaborative Filtering Recommender SystemsCold-Start Recommendation OptimizationCross-Domain Recommendation SystemUser/Item Embedding Generation
The ALLMRec system combines collaborative knowledge with large language models to excel in both cold and warm start scenarios, enhancing user experience while being modelagnostic and efficient.
02
Towards Scalable Semantic Representation for Recommendation
Published:10/12/2024
LLM-based Recommendation SystemsSemantic ID ModelingHigh-Dimensional Embedding Dimensionality ReductionMixture-of-Codes for RecommendationRecommendation System Performance Enhancement
This study introduces the MixtureofCodes (MoC) method to address dimensionality compression when integrating LLM embeddings into recommendation systems. By constructing multiple independent codebooks and incorporating a fusion module, MoC significantly enhances the discriminabi
04
Towards Next-Generation Recommender Systems: A Benchmark for Personalized Recommendation Assistant with LLMs
Published:3/12/2025
LLM-based Recommendation SystemsPersonalized Recommendation Assistant BenchmarkRecommendation System Performance EvaluationComplex User Query HandlingLLM Capability Assessment
The paper introduces RecBench, a benchmark dataset assessing LLMs in handling complex personalized recommendation tasks, revealing that while LLMs show initial capabilities as assistants, they struggle with reasoning and misleading queries.
01
Recommender Systems in the Era of Large Language Models (LLMs)
Published:7/5/2023
LLM-based Recommendation SystemsLarge Language Model Fine-TuningGenerative Recommendation SystemsPre-training and Fine-tuning in Recommender SystemsPrompting Methods for Large Language Models
This paper reviews techniques for enhancing recommender systems using Large Language Models (LLMs), focusing on pretraining, finetuning, and prompting. It highlights LLMs' potential in feature encoding and their future applications in recommender system research.
04
Align$^3$GR: Unified Multi-Level Alignment for LLM-based Generative Recommendation
Published:11/14/2025
LLM-based Recommendation SystemsMulti-Level Alignment MethodsBehavior Modeling and AlignmentDynamic Preference AdaptationSelf-Play Decision Optimization
Align3^3GR effectively transforms LLMs into recommendation systems via a unified multilevel alignment approach, introducing dual tokenization, enhanced behavior modeling, and progressive decision optimization. It significantly outperforms stateoftheart metrics.
07
USB-Rec: An Effective Framework for Improving Conversational Recommendation Capability of Large Language Model
Published:9/21/2025
RL Training for Large Language ModelsConversational Recommender SystemsLLM-based Recommendation SystemsUser-Simulator-Based FrameworkPreference Optimization Dataset Construction
The USBRec framework enhances Large Language Models' capabilities in conversational recommendation through a usersimulatorbased preference optimization dataset and a selfenhancement strategy. Extensive experiments show it consistently outperforms existing stateoftheart met
04
Modeling shopper interest broadness with entropy-driven dialogue policy in the context of arbitrarily large product catalogs
Published:9/8/2025
Conversational Recommender SystemsLLM-based Recommendation SystemsUser Interest Broadness ModelingEntropy-Driven Dialogue PolicyDynamic Exploration and Exploitation in Recommendations
This study introduces a conversational recommender system strategy that balances exploration and exploitation by modeling user interest breadth through retrieval score entropy, dynamically adjusting dialogue policies based on query specificity to enhance user experience.
03
Generative Sequential Recommendation with GPTRec
Published:6/20/2023
Sequential Recommender SystemsLLM-based Recommendation SystemsGPT-2-based Recommendation ModelSub-ID Tokenisation AlgorithmNext-K Generative Recommendation Strategy
GPTRec, a GPT2based generative sequential recommender, uses SVD tokenization to handle large vocabularies and a NextK strategy to optimize recommendations, achieving SASReclevel quality on MovieLens1M with 40% smaller embeddings.
03
A Survey on Generative Recommendation: Data, Model, and Tasks
Published:10/31/2025
Generative Recommendation SystemsLarge Language Model Fine-TuningDiffusion ModelsMultimodal Large Language ModelLLM-based Recommendation Systems
This survey reviews generative recommendation via a unified framework, analyzing data augmentation, model alignment, and task design, highlighting innovations in large language and diffusion models that enable knowledge integration, natural language understanding, and personalize
011
MMQ-v2: Align, Denoise, and Amplify: Adaptive Behavior Mining for Semantic IDs Learning in Recommendation
Published:10/29/2025
Generative Recommendation SystemsLLM-based Recommendation SystemsAdaptive Behavior MiningSemantic IDs LearningContent-Behavior Multimodal Alignment
MMQv2 adaptively aligns, denoises, and amplifies multimodal signals to enhance semantic ID learning, overcoming noise and signal ambiguity in recommendation systems, leading to superior performance on largescale datasets.
023
Beyond Persuasion: Towards Conversational Recommender System with Credible Explanations
Published:9/22/2024
LLM-based Recommendation SystemsGenerative Recommendation SystemsCredible Explanation GenerationConversational Recommender Systems
This paper proposes PCCRS, enhancing conversational recommenders with credibilityaware strategies and posthoc selfreflection, improving both explanation trustworthiness and recommendation accuracy.
02
CARE: Contextual Adaptation of Recommenders for LLM-based Conversational Recommendation
Published:8/19/2025
LLM-based Recommendation SystemsConversational Recommender SystemsContext-Aware RecommendationEntity-Level Recommendation EnhancementRecommendation Reranking
CARE framework integrates external recommenders with LLMs, enabling domain adaptation and leveraging context and collaborative relationships to improve accuracy and diversity in conversational recommendations.
03
ChatCRS: Incorporating External Knowledge and Goal Guidance for LLM-based Conversational Recommender Systems
Published:4/1/2025
LLM-based Recommendation SystemsExternal Knowledge Retrieval IntegrationDialogue Goal PlanningMulti-Goal Conversational Recommender Systems
ChatCRS integrates external knowledge and goal planning via toolaugmented agents, enhancing multigoal conversational recommendation. It significantly improves recommendation accuracy and language quality, establishing stateoftheart results.
07
PAARS: Persona Aligned Agentic Retail Shoppers
Published:3/31/2025
LLM-based Recommendation SystemsOnline Shopping Behavior ModelingPersona Generation and ApplicationAgent Behavior SimulationConsumer Behavior Distribution Alignment
PAARS framework creates personadriven retail agents equipped with shopping tools and aligns their grouplevel behavior distributions with humans, improving simulation accuracy and enabling automated A/B testing applications.
03
LLMs Reproduce Human Purchase Intent via Semantic Similarity Elicitation of Likert Ratings
Published:10/9/2025
Large Language Model Fine-TuningLLM-based Recommendation SystemsSemantic Similarity Rating MethodsLikert Scale SimulationConsumer Behavior Modeling
SSR method maps LLMs' textual responses via semantic similarity to replicate human purchase intent with 90% testretest reliability, preserving realistic survey response patterns and interpretability, enabling scalable consumer research simulation.
011
R4ec: A Reasoning, Reflection, and Refinement Framework for Recommendation Systems
Published:7/23/2025
Generative Recommendation SystemsRL Training for Large Language ModelsSequential Recommender SystemsLLM-based Recommendation SystemsReasoning, Reflection, and Refinement Framework
R4ec integrates reasoning, reflection, and refinement with actor and reflection models to iteratively optimize recommendations, enabling a System2like approach. Experiments demonstrate its superior performance and increased revenue in largescale realworld applications.
03