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

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xia, Runze, Ji, Yupeng, Zhou, Yuxi, Liu, Haodong, Zhang, Teng, Li, Piji
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Information Retrieval Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Distilling Reasoning Without Knowledge: A Framework for Reliable LLMs
di: Kietkajornrit, Auksarapak, et al.
Pubblicazione: (2026)

SelfGNN: Self-Supervised Graph Neural Networks for Sequential Recommendation
di: Liu, Yuxi, et al.
Pubblicazione: (2024)

PRECTR: A Synergistic Framework for Integrating Personalized Search Relevance Matching and CTR Prediction
di: Chen, Rong, et al.
Pubblicazione: (2025)

MACA: A Framework for Distilling Trustworthy LLMs into Efficient Retrievers
di: Gudipudi, Satya Swaroop, et al.
Pubblicazione: (2026)

SD-Search: On-Policy Hindsight Self-Distillation for Search-Augmented Reasoning
di: Ma, Yufei, et al.
Pubblicazione: (2026)

Towards Boosting LLMs-driven Relevance Modeling with Progressive Retrieved Behavior-augmented Prompting
di: Chen, Zeyuan, et al.
Pubblicazione: (2024)

Search-E1: Self-Distillation Drives Self-Evolution in Search-Augmented Reasoning
di: Liang, Zihan, et al.
Pubblicazione: (2026)

CPRM: A LLM-based Continual Pre-training Framework for Relevance Modeling in Commercial Search
di: Wu, Kaixin, et al.
Pubblicazione: (2024)

SocRipple: A Two-Stage Framework for Cold-Start Video Recommendations
di: Jaspal, Amit, et al.
Pubblicazione: (2025)

Optimizing Generative Ranking Relevance via Reinforcement Learning in Xiaohongshu Search
di: Zeng, Ziyang, et al.
Pubblicazione: (2025)

DELRec: Distilling Sequential Pattern to Enhance LLMs-based Sequential Recommendation
di: Zhang, Haoyi, et al.
Pubblicazione: (2024)

Bridging Semantic Understanding and Popularity Bias with LLMs
di: Luo, Renqiang, et al.
Pubblicazione: (2026)

R3A: Reinforced Reasoning for Relevance Assessment for RAG in User-Generated Content Platforms
di: Yuan, Xiaowei, et al.
Pubblicazione: (2025)

Towards Competitive Search Relevance For Inference-Free Learned Sparse Retrievers
di: Geng, Zhichao, et al.
Pubblicazione: (2024)

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

When LLMs Disagree: Diagnosing Relevance Filtering Bias and Retrieval Divergence in SDG Search
di: Ingram, William A., et al.
Pubblicazione: (2025)

AutoMIR: Effective Zero-Shot Medical Information Retrieval without Relevance Labels
di: Li, Lei, et al.
Pubblicazione: (2024)

TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance
di: Yang, Jianhui, et al.
Pubblicazione: (2025)

PoTable: Towards Systematic Thinking via Plan-then-Execute Stage Reasoning on Tables
di: Mao, Qingyang, et al.
Pubblicazione: (2024)

Xinyu AI Search: Enhanced Relevance and Comprehensive Results with Rich Answer Presentations
di: Tang, Bo, et al.
Pubblicazione: (2025)

LREF: A Novel LLM-based Relevance Framework for E-commerce
di: Tang, Tian, et al.
Pubblicazione: (2025)

DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrieval
di: Sun, Duolin, et al.
Pubblicazione: (2025)

Distillation-based Scenario-Adaptive Mixture-of-Experts for the Matching Stage of Multi-scenario Recommendation
di: Wang, Ruibing, et al.
Pubblicazione: (2025)

Are LLMs Reliable Rankers? Rank Manipulation via Two-Stage Token Optimization
di: Xing, Tiancheng, et al.
Pubblicazione: (2025)

Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
di: Jin, Bowen, et al.
Pubblicazione: (2025)

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

Iterative Semantic Reasoning from Individual to Group Interests for Generative Recommendation with LLMs
di: Zhu, Xiaofei, et al.
Pubblicazione: (2026)

A model and package for German ColBERT
di: Dang, Thuong, et al.
Pubblicazione: (2025)

Explainable LLM-driven Multi-dimensional Distillation for E-Commerce Relevance Learning
di: Zhao, Gang, et al.
Pubblicazione: (2024)

Does Reasoning Make Search More Fair? Comparing Fairness in Reasoning and Non-Reasoning Rerankers
di: Samuel, Saron, et al.
Pubblicazione: (2026)

TaoSR1: The Thinking Model for E-commerce Relevance Search
di: Dong, Chenhe, et al.
Pubblicazione: (2025)

Search-o1: Agentic Search-Enhanced Large Reasoning Models
di: Li, Xiaoxi, et al.
Pubblicazione: (2025)

OneSearch-V2: The Latent Reasoning Enhanced Self-distillation Generative Search Framework
di: Chen, Ben, et al.
Pubblicazione: (2026)

An Iterative Utility Judgment Framework Inspired by Philosophical Relevance via LLMs
di: Zhang, Hengran, et al.
Pubblicazione: (2024)

DTKG: Dual-Track Knowledge Graph-Verified Reasoning Framework for Multi-Hop QA
di: Wang, Changhao, et al.
Pubblicazione: (2025)

Relevance meets Diversity: A User-Centric Framework for Knowledge Exploration through Recommendations
di: Coppolillo, Erica, et al.
Pubblicazione: (2024)

Improve Rule Retrieval and Reasoning with Self-Induction and Relevance ReEstimate
di: Huang, Ziyang, et al.
Pubblicazione: (2025)

RAG-R1: Incentivizing the Search and Reasoning Capabilities of LLMs through Multi-query Parallelism
di: Tan, Zhiwen, et al.
Pubblicazione: (2025)

BERT and CNN integrated Neural Collaborative Filtering for Recommender Systems
di: Munem, Abdullah Al, et al.
Pubblicazione: (2025)

BiXSE: Improving Dense Retrieval via Probabilistic Graded Relevance Distillation
di: Tsirigotis, Christos, et al.
Pubblicazione: (2025)