Copertina

MSL: Not All Tokens Are What You Need for Tuning LLM as a Recommender

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Bohao, Liu, Feng, Chen, Jiawei, Lou, Xingyu, Zhang, Changwang, Wang, Jun, Sun, Yuegang, Feng, Yan, Chen, Chun, Wang, Can
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Information Retrieval
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

HatLLM: Hierarchical Attention Masking for Enhanced Collaborative Modeling in LLM-based Recommendation
di: Cui, Yu, et al.
Pubblicazione: (2025)

Bridging the Gap: Self-Optimized Fine-Tuning for LLM-based Recommender Systems
di: Tang, Heng, et al.
Pubblicazione: (2025)

Does LLM Focus on the Right Words? Mitigating Context Bias in LLM-based Recommenders
di: Wang, Bohao, et al.
Pubblicazione: (2025)

LLM4DSR: Leveraging Large Language Model for Denoising Sequential Recommendation
di: Wang, Bohao, et al.
Pubblicazione: (2024)

Field Matters: A Lightweight LLM-enhanced Method for CTR Prediction
di: Cui, Yu, et al.
Pubblicazione: (2025)

SpecTran: Spectral-Aware Transformer-based Adapter for LLM-Enhanced Sequential Recommendation
di: Cui, Yu, et al.
Pubblicazione: (2026)

Distributionally Robust Graph-based Recommendation System
di: Wang, Bohao, et al.
Pubblicazione: (2024)

Breaking the Top-$K$ Barrier: Advancing Top-$K$ Ranking Metrics Optimization in Recommender Systems
di: Yang, Weiqin, et al.
Pubblicazione: (2025)

Distillation Matters: Empowering Sequential Recommenders to Match the Performance of Large Language Model
di: Cui, Yu, et al.
Pubblicazione: (2024)

Rankformer: A Graph Transformer for Recommendation based on Ranking Objective
di: Chen, Sirui, et al.
Pubblicazione: (2025)

SIGformer: Sign-aware Graph Transformer for Recommendation
di: Chen, Sirui, et al.
Pubblicazione: (2024)

Action is All You Need: Dual-Flow Generative Ranking Network for Recommendation
di: Guo, Hao, et al.
Pubblicazione: (2025)

Architecture is All You Need: Improving LLM Recommenders by Dropping the Text
di: Foley, Kevin, et al.
Pubblicazione: (2025)

FAIR: Focused Attention Is All You Need for Generative Recommendation
di: Xiao, Longtao, et al.
Pubblicazione: (2025)

Talos: Optimizing Top-$K$ Accuracy in Recommender Systems
di: Zhang, Shengjia, et al.
Pubblicazione: (2026)

How Do Recommendation Models Amplify Popularity Bias? An Analysis from the Spectral Perspective
di: Lin, Siyi, et al.
Pubblicazione: (2024)

Adaptive Conditional Expert Selection Network for Multi-domain Recommendation
di: Dong, Kuiyao, et al.
Pubblicazione: (2024)

PSL: Rethinking and Improving Softmax Loss from Pairwise Perspective for Recommendation
di: Yang, Weiqin, et al.
Pubblicazione: (2024)

TopKGAT: A Top-K Objective-Driven Architecture for Recommendation
di: Chen, Sirui, et al.
Pubblicazione: (2026)

Multi-LLM Token Filtering and Routing for Sequential Recommendation
di: Chen, Wuhan, et al.
Pubblicazione: (2026)

BEAR: Towards Beam-Search-Aware Optimization for Recommendation with Large Language Models
di: Yang, Weiqin, et al.
Pubblicazione: (2026)

Advancing Loss Functions in Recommender Systems: A Comparative Study with a Rényi Divergence-Based Solution
di: Zhang, Shengjia, et al.
Pubblicazione: (2025)

OThink-MR1: Stimulating multimodal generalized reasoning capabilities via dynamic reinforcement learning
di: Liu, Zhiyuan, et al.
Pubblicazione: (2025)

Dot Product is All You Need: Bridging the Gap Between Item Recommendation and Link Prediction
di: Malitesta, Daniele, et al.
Pubblicazione: (2024)

Beyong Tokens: Item-aware Attention for LLM-based Recommendation
di: Zhang, Xiaokun, et al.
Pubblicazione: (2026)

Language Representations Can be What Recommenders Need: Findings and Potentials
di: Sheng, Leheng, et al.
Pubblicazione: (2024)

Trustworthy Recommendation in the Era of Large Language Models: Opportunities and Challenges
di: Wang, Bohao, et al.
Pubblicazione: (2026)

Learnable Item Tokenization for Generative Recommendation
di: Wang, Wenjie, et al.
Pubblicazione: (2024)

Causal Deconfounding via Confounder Disentanglement for Dual-Target Cross-Domain Recommendation
di: Zhu, Jiajie, et al.
Pubblicazione: (2024)

Generate and Instantiate What You Prefer: Text-Guided Diffusion for Sequential Recommendation
di: Hu, Guoqing, et al.
Pubblicazione: (2024)

EARN: Efficient Inference Acceleration for LLM-based Generative Recommendation by Register Tokens
di: Yang, Chaoqun, et al.
Pubblicazione: (2025)

Heterogeneous User Modeling for LLM-based Recommendation
di: Bao, Honghui, et al.
Pubblicazione: (2025)

Let Me Do It For You: Towards LLM Empowered Recommendation via Tool Learning
di: Zhao, Yuyue, et al.
Pubblicazione: (2024)

Bi-Level Optimization for Generative Recommendation: Bridging Tokenization and Generation
di: Bai, Yimeng, et al.
Pubblicazione: (2025)

Real-Time Personalization for LLM-based Recommendation with Customized In-Context Learning
di: Bao, Keqin, et al.
Pubblicazione: (2024)

Discrete Preference Learning for Personalized Multimodal Generation
di: Zhang, Yuting, et al.
Pubblicazione: (2026)

Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation
di: Wang, Shijie, et al.
Pubblicazione: (2025)

Token-level Collaborative Alignment for LLM-based Generative Recommendation
di: Lin, Fake, et al.
Pubblicazione: (2026)

Decoding in Latent Spaces for Efficient Inference in LLM-based Recommendation
di: Wang, Chengbing, et al.
Pubblicazione: (2025)

DIIT: A Domain-Invariant Information Transfer Method for Industrial Cross-Domain Recommendation
di: Huang, Heyuan, et al.
Pubblicazione: (2024)