Image de couverture de livre

From Reasoning LLMs to BERT: A Two-Stage Distillation Framework for Search Relevance

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xia, Runze, Ji, Yupeng, Zhou, Yuxi, Liu, Haodong, Zhang, Teng, Li, Piji
Format:	Preprint
Publié:	2025
Sujets:	Information Retrieval Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Distilling Reasoning Without Knowledge: A Framework for Reliable LLMs
par: Kietkajornrit, Auksarapak, et autres
Publié: (2026)

SelfGNN: Self-Supervised Graph Neural Networks for Sequential Recommendation
par: Liu, Yuxi, et autres
Publié: (2024)

PRECTR: A Synergistic Framework for Integrating Personalized Search Relevance Matching and CTR Prediction
par: Chen, Rong, et autres
Publié: (2025)

MACA: A Framework for Distilling Trustworthy LLMs into Efficient Retrievers
par: Gudipudi, Satya Swaroop, et autres
Publié: (2026)

SD-Search: On-Policy Hindsight Self-Distillation for Search-Augmented Reasoning
par: Ma, Yufei, et autres
Publié: (2026)

Towards Boosting LLMs-driven Relevance Modeling with Progressive Retrieved Behavior-augmented Prompting
par: Chen, Zeyuan, et autres
Publié: (2024)

Search-E1: Self-Distillation Drives Self-Evolution in Search-Augmented Reasoning
par: Liang, Zihan, et autres
Publié: (2026)

CPRM: A LLM-based Continual Pre-training Framework for Relevance Modeling in Commercial Search
par: Wu, Kaixin, et autres
Publié: (2024)

SocRipple: A Two-Stage Framework for Cold-Start Video Recommendations
par: Jaspal, Amit, et autres
Publié: (2025)

Optimizing Generative Ranking Relevance via Reinforcement Learning in Xiaohongshu Search
par: Zeng, Ziyang, et autres
Publié: (2025)

DELRec: Distilling Sequential Pattern to Enhance LLMs-based Sequential Recommendation
par: Zhang, Haoyi, et autres
Publié: (2024)

Bridging Semantic Understanding and Popularity Bias with LLMs
par: Luo, Renqiang, et autres
Publié: (2026)

R3A: Reinforced Reasoning for Relevance Assessment for RAG in User-Generated Content Platforms
par: Yuan, Xiaowei, et autres
Publié: (2025)

Towards Competitive Search Relevance For Inference-Free Learned Sparse Retrievers
par: Geng, Zhichao, et autres
Publié: (2024)

PRECTR-V2:Unified Relevance-CTR Framework with Cross-User Preference Mining, Exposure Bias Correction, and LLM-Distilled Encoder Optimization
par: Cao, Shuzhi, et autres
Publié: (2026)

When LLMs Disagree: Diagnosing Relevance Filtering Bias and Retrieval Divergence in SDG Search
par: Ingram, William A., et autres
Publié: (2025)

AutoMIR: Effective Zero-Shot Medical Information Retrieval without Relevance Labels
par: Li, Lei, et autres
Publié: (2024)

TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance
par: Yang, Jianhui, et autres
Publié: (2025)

PoTable: Towards Systematic Thinking via Plan-then-Execute Stage Reasoning on Tables
par: Mao, Qingyang, et autres
Publié: (2024)

Xinyu AI Search: Enhanced Relevance and Comprehensive Results with Rich Answer Presentations
par: Tang, Bo, et autres
Publié: (2025)

LREF: A Novel LLM-based Relevance Framework for E-commerce
par: Tang, Tian, et autres
Publié: (2025)

DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrieval
par: Sun, Duolin, et autres
Publié: (2025)

Distillation-based Scenario-Adaptive Mixture-of-Experts for the Matching Stage of Multi-scenario Recommendation
par: Wang, Ruibing, et autres
Publié: (2025)

Are LLMs Reliable Rankers? Rank Manipulation via Two-Stage Token Optimization
par: Xing, Tiancheng, et autres
Publié: (2025)

Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
par: Jin, Bowen, et autres
Publié: (2025)

Towards a Theoretical Understanding of Two-Stage Recommender Systems
par: Jaiswal, Amit Kumar
Publié: (2024)

Iterative Semantic Reasoning from Individual to Group Interests for Generative Recommendation with LLMs
par: Zhu, Xiaofei, et autres
Publié: (2026)

A model and package for German ColBERT
par: Dang, Thuong, et autres
Publié: (2025)

Explainable LLM-driven Multi-dimensional Distillation for E-Commerce Relevance Learning
par: Zhao, Gang, et autres
Publié: (2024)

Does Reasoning Make Search More Fair? Comparing Fairness in Reasoning and Non-Reasoning Rerankers
par: Samuel, Saron, et autres
Publié: (2026)

TaoSR1: The Thinking Model for E-commerce Relevance Search
par: Dong, Chenhe, et autres
Publié: (2025)

Search-o1: Agentic Search-Enhanced Large Reasoning Models
par: Li, Xiaoxi, et autres
Publié: (2025)

OneSearch-V2: The Latent Reasoning Enhanced Self-distillation Generative Search Framework
par: Chen, Ben, et autres
Publié: (2026)

An Iterative Utility Judgment Framework Inspired by Philosophical Relevance via LLMs
par: Zhang, Hengran, et autres
Publié: (2024)

DTKG: Dual-Track Knowledge Graph-Verified Reasoning Framework for Multi-Hop QA
par: Wang, Changhao, et autres
Publié: (2025)

Relevance meets Diversity: A User-Centric Framework for Knowledge Exploration through Recommendations
par: Coppolillo, Erica, et autres
Publié: (2024)

Improve Rule Retrieval and Reasoning with Self-Induction and Relevance ReEstimate
par: Huang, Ziyang, et autres
Publié: (2025)

RAG-R1: Incentivizing the Search and Reasoning Capabilities of LLMs through Multi-query Parallelism
par: Tan, Zhiwen, et autres
Publié: (2025)

BERT and CNN integrated Neural Collaborative Filtering for Recommender Systems
par: Munem, Abdullah Al, et autres
Publié: (2025)

BiXSE: Improving Dense Retrieval via Probabilistic Graded Relevance Distillation
par: Tsirigotis, Christos, et autres
Publié: (2025)