Image de couverture de livre

Think When Needed: Model-Aware Reasoning Routing for LLM-based Ranking

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Guo, Huizhong, Wei, Tianjun, Wang, Dongxia, Du, Yingpeng, Wang, Ziyan, Zhang, Jie, Sun, Zhu
Format:	Preprint
Publié:	2026
Sujets:	Information Retrieval
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Mirroring Users: Towards Building Preference-aligned User Simulator with User Feedback in Recommendation
par: Wei, Tianjun, et autres
Publié: (2025)

LLM-Driven Dual-Level Multi-Interest Modeling for Recommendation
par: Wang, Ziyan, et autres
Publié: (2025)

MMGRid: Navigating Temporal-aware and Cross-domain Generative Recommendation via Model Merging
par: Wei, Tianjun, et autres
Publié: (2026)

Enhancing New-item Fairness in Dynamic Recommender Systems
par: Guo, Huizhong, et autres
Publié: (2025)

LightKG: Efficient Knowledge-Aware Recommendations with Simplified GNN Architecture
par: Li, Yanhui, et autres
Publié: (2025)

Active Large Language Model-based Knowledge Distillation for Session-based Recommendation
par: Du, Yingpeng, et autres
Publié: (2024)

TFRank: Think-Free Reasoning Enables Practical Pointwise LLM Ranking
par: Fan, Yongqi, et autres
Publié: (2025)

Diagnostic-Guided Dynamic Profile Optimization for LLM-based User Simulators in Sequential Recommendation
par: Liu, Hongyang, et autres
Publié: (2025)

MRP-LLM: Multitask Reflective Large Language Models for Privacy-Preserving Next POI Recommendation
par: Wu, Ziqing, et autres
Publié: (2024)

Shilling Recommender Systems by Generating Side-feature-aware Fake User Profiles
par: Wang, Yuanrong, et autres
Publié: (2025)

REALM: Recursive Relevance Modeling for LLM-based Document Re-Ranking
par: Wang, Pinhuan, et autres
Publié: (2025)

Reasoning to Rank: An End-to-End Solution for Exploiting Large Language Models for Recommendation
par: Zheng, Kehan, et autres
Publié: (2026)

Internalizing Multi-Agent Reasoning for Accurate and Efficient LLM-based Recommendation
par: Wu, Yang, et autres
Publié: (2026)

ThinkRec: Thinking-based recommendation via LLM
par: Yu, Qihang, et autres
Publié: (2025)

SG-LegalCite: A Principle-Augmented Benchmark for Legal Citation Retrieval in Singapore Law
par: Ern, Shannon Lee Yueh, et autres
Publié: (2026)

RankSteer: Activation Steering for Pointwise LLM Ranking
par: Wang, Yumeng, et autres
Publié: (2026)

When should I search more: Adaptive Complex Query Optimization with Reinforcement Learning
par: Wen, Wei, et autres
Publié: (2026)

Verifiable Reasoning for LLM-based Generative Recommendation
par: Lin, Xinyu, et autres
Publié: (2026)

BracketRank: Large Language Model Document Ranking via Reasoning-based Competitive Elimination
par: Abdallah, Abdelrahman, et autres
Publié: (2026)

OneRec-Think: In-Text Reasoning for Generative Recommendation
par: Liu, Zhanyu, et autres
Publié: (2025)

RankMixer: Scaling Up Ranking Models in Industrial Recommenders
par: Zhu, Jie, et autres
Publié: (2025)

Heterogeneous User Modeling for LLM-based Recommendation
par: Bao, Honghui, et autres
Publié: (2025)

MSL: Not All Tokens Are What You Need for Tuning LLM as a Recommender
par: Wang, Bohao, et autres
Publié: (2025)

Action is All You Need: Dual-Flow Generative Ranking Network for Recommendation
par: Guo, Hao, et autres
Publié: (2025)

Think When Needed: Adaptive Reasoning-Driven Multimodal Embeddings with a Dual-LoRA Architecture
par: Zhang, Longxiang, et autres
Publié: (2026)

SpecTran: Spectral-Aware Transformer-based Adapter for LLM-Enhanced Sequential Recommendation
par: Cui, Yu, et autres
Publié: (2026)

Can LLM Annotations Replace User Clicks for Learning to Rank?
par: Yu, Lulu, et autres
Publié: (2025)

Factorized Latent Reasoning for LLM-based Recommendation
par: Gao, Tianqi, et autres
Publié: (2026)

DSFNet: Learning Disentangled Scenario Factorization for Multi-Scenario Route Ranking
par: Yu, Jiahao, et autres
Publié: (2024)

RAGRouter-Bench: A Dataset and Benchmark for Adaptive RAG Routing
par: Wang, Ziqi, et autres
Publié: (2026)

The Ranking Blind Spot: Decision Hijacking in LLM-based Text Ranking
par: Qian, Yaoyao, et autres
Publié: (2025)

HatLLM: Hierarchical Attention Masking for Enhanced Collaborative Modeling in LLM-based Recommendation
par: Cui, Yu, et autres
Publié: (2025)

Not Just What, But When: Integrating Irregular Intervals to LLM for Sequential Recommendation
par: Du, Wei-Wei, et autres
Publié: (2025)

Batched Self-Consistency Improves LLM Relevance Assessment and Ranking
par: Korikov, Anton, et autres
Publié: (2025)

Rank-GRPO: Training LLM-based Conversational Recommender Systems with Reinforcement Learning
par: Zhu, Yaochen, et autres
Publié: (2025)

SPARK: Adaptive Low-Rank Knowledge Graph Modeling in Hybrid Geometric Spaces for Recommendation
par: Wang, Binhao, et autres
Publié: (2025)

GoalRank: Group-Relative Optimization for a Large Ranking Model
par: Zhang, Kaike, et autres
Publié: (2025)

Act-With-Think: Chunk Auto-Regressive Modeling for Generative Recommendation
par: Wang, Yifan, et autres
Publié: (2025)

Why Thinking Hurts: Diagnosing and Rectifying Linguistic Inertia in Large Language Models for Recommendation
par: Zhang, Luankang, et autres
Publié: (2026)

asLLR: LLM based Leads Ranking in Auto Sales
par: Sun, Yin, et autres
Publié: (2025)