Imagen de Portada

Multi-stage Large Language Model Pipelines Can Outperform GPT-4o in Relevance Assessment

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Schnabel, Julian A., Trippas, Johanne R., Scholer, Falk, Hettiachchi, Danula
Formato:	Preprint
Publicado:	2025
Materias:	Information Retrieval H.3.3
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Characterizing Information Seeking Processes with Multiple Physiological Signals
por: Ji, Kaixin, et al.
Publicado: (2024)

PUB: An LLM-Enhanced Personality-Driven User Behaviour Simulator for Recommender System Evaluation
por: Ma, Chenglong, et al.
Publicado: (2025)

Control Search Rankings, Control the World: What is a Good Search Engine?
por: Coghlan, Simon, et al.
Publicado: (2025)

Formalized Information Needs Improve Large-Language-Model Relevance Judgments
por: Keller, Jüri, et al.
Publicado: (2026)

LLM-Assisted Relevance Assessments: When Should We Ask LLMs for Help?
por: Takehi, Rikiya, et al.
Publicado: (2024)

Relevance Filtering for Embedding-based Retrieval
por: Rossi, Nicholas, et al.
Publicado: (2024)

Enhancing Relevance of Embedding-based Retrieval at Walmart
por: Lin, Juexin, et al.
Publicado: (2024)

Where Relevance Emerges: A Layer-Wise Study of Internal Attention for Zero-Shot Re-Ranking
por: Chen, Haodong, et al.
Publicado: (2026)

Text-like Encoding of Collaborative Information in Large Language Models for Recommendation
por: Zhang, Yang, et al.
Publicado: (2024)

Can we predict QPP? An approach based on multivariate outliers
por: Chifu, Adrian-Gabriel, et al.
Publicado: (2024)

Response Quality Assessment for Retrieval-Augmented Generation via Conditional Conformal Factuality
por: Feng, Naihe, et al.
Publicado: (2025)

GPT4Rec: Graph Prompt Tuning for Streaming Recommendation
por: Zhang, Peiyan, et al.
Publicado: (2024)

Diagnosing LLM-based Rerankers in Cold-Start Recommender Systems: Coverage, Exposure and Practical Mitigations
por: Lemdiasova, Ekaterina, et al.
Publicado: (2026)

JointRank: Rank Large Set with Single Pass
por: Dedov, Evgeny
Publicado: (2025)

Comprehensive List Generation for Multi-Generator Reranking
por: Yang, Hailan, et al.
Publicado: (2025)

WindTunnel -- A Framework for Community Aware Sampling of Large Corpora
por: Iannelli, Michael
Publicado: (2024)

MIRA: An LLM-Assisted Benchmark for Multi-Category Integrated Retrieval
por: Türkmen, Mehmet Deniz, et al.
Publicado: (2026)

ESANS: Effective and Semantic-Aware Negative Sampling for Large-Scale Retrieval Systems
por: Xing, Haibo, et al.
Publicado: (2025)

A Brief Comparison of Training-Free Multi-Vector Sequence Compression Methods
por: Jha, Rohan, et al.
Publicado: (2026)

CSMF: Cascaded Selective Mask Fine-Tuning for Multi-Objective Embedding-Based Retrieval
por: Deng, Hao, et al.
Publicado: (2025)

FIM: Frequency-Aware Multi-View Interest Modeling for Local-Life Service Recommendation
por: Wang, Guoquan, et al.
Publicado: (2025)

MIND Your Language: A Multilingual Dataset for Cross-lingual News Recommendation
por: Iana, Andreea, et al.
Publicado: (2024)

Multi-Granularity Distribution Modeling for Video Watch Time Prediction via Exponential-Gaussian Mixture Network
por: Zhao, Xu, et al.
Publicado: (2025)

Understanding Before Recommendation: Semantic Aspect-Aware Review Exploitation via Large Language Models
por: Liu, Fan, et al.
Publicado: (2023)

Large Language Models for Relevance Judgment in Product Search
por: Mehrdad, Navid, et al.
Publicado: (2024)

Boosting LLM-based Relevance Modeling with Distribution-Aware Robust Learning
por: Liu, Hong, et al.
Publicado: (2024)

Best in Tau@LLMJudge: Criteria-Based Relevance Evaluation with Llama3
por: Farzi, Naghmeh, et al.
Publicado: (2024)

A Robust and Efficient Pipeline for Enterprise-Level Large-Scale Entity Resolution
por: Kannangara, Sandeepa, et al.
Publicado: (2025)

Criteria-Based LLM Relevance Judgments
por: Farzi, Naghmeh, et al.
Publicado: (2025)

GradCraft: Elevating Multi-task Recommendations through Holistic Gradient Crafting
por: Bai, Yimeng, et al.
Publicado: (2024)

Online Item Cold-Start Recommendation with Popularity-Aware Meta-Learning
por: Luo, Yunze, et al.
Publicado: (2024)

Exploring Content-Based and Meta-Data Analysis for Detecting Fake News Infodemic: A case study on COVID-19
por: Ajao, Oluwaseun, et al.
Publicado: (2024)

An Intrinsic Framework of Information Retrieval Evaluation Measures
por: Giner, Fernando
Publicado: (2023)

Content-Aware Tweet Location Inference using Quadtree Spatial Partitioning and Jaccard-Cosine Word Embedding
por: Ajao, Oluwaseun, et al.
Publicado: (2024)

ColBERT's [MASK]-based Query Augmentation: Effects of Quadrupling the Query Input Length
por: Giacalone, Ben, et al.
Publicado: (2024)

Cluster-based Graph Collaborative Filtering
por: Liu, Fan, et al.
Publicado: (2024)

Improving E-commerce Search with Category-Aligned Retrieval
por: Aliev, Rauf
Publicado: (2025)

Hyena Operator for Fast Sequential Recommendation
por: Liu, Jiahao, et al.
Publicado: (2026)

Graph Reasoning for Explainable Cold Start Recommendation
por: Frej, Jibril, et al.
Publicado: (2024)

CreAgent: Towards Long-Term Evaluation of Recommender System under Platform-Creator Information Asymmetry
por: Ye, Xiaopeng, et al.
Publicado: (2025)