Copertina

Dynamic Ranked List Truncation for Reranking Pipelines via LLM-generated Reference-Documents

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Sinhababu, Nilanjan, Bharati, Soumedhik, Ganguly, Debasis, Mitra, Pabitra
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Information Retrieval
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Modeling Ranking Properties with In-Context Learning
di: Sinhababu, Nilanjan, et al.
Pubblicazione: (2025)

Few-shot Prompting for Pairwise Ranking: An Effective Non-Parametric Retrieval Model
di: Sinhababu, Nilanjan, et al.
Pubblicazione: (2024)

Top-Down Partitioning for Efficient List-Wise Ranking
di: Parry, Andrew, et al.
Pubblicazione: (2024)

LURE-RAG: Lightweight Utility-driven Reranking for Efficient RAG
di: Chandra, Manish, et al.
Pubblicazione: (2026)

Disentangling Locality and Entropy in Ranking Distillation
di: Parry, Andrew, et al.
Pubblicazione: (2025)

UniRank: Unified List-wise Reranking via Confidence-Ordered Denoising
di: Jia, Pengyue, et al.
Pubblicazione: (2026)

T-Retrievability: A Topic-Focused Approach to Measure Fair Document Exposure in Information Retrieval
di: Chang, Xuejun, et al.
Pubblicazione: (2025)

EviRerank: Adaptive Evidence Construction for Long-Document LLM Reranking
di: Li, Minghan, et al.
Pubblicazione: (2024)

RankLLM: A Python Package for Reranking with LLMs
di: Sharifymoghaddam, Sahel, et al.
Pubblicazione: (2025)

Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning
di: Zhuang, Shengyao, et al.
Pubblicazione: (2025)

List-aware Reranking-Truncation Joint Model for Search and Retrieval-augmented Generation
di: Xu, Shicheng, et al.
Pubblicazione: (2024)

CoRank: LLM-Based Compact Reranking with Document Features for Scientific Retrieval
di: Tian, Runchu, et al.
Pubblicazione: (2025)

SumRank: Aligning Summarization Models for Long-Document Listwise Reranking
di: Feng, Jincheng, et al.
Pubblicazione: (2026)

Breaking Flat: A Generalised Query Performance Prediction Evaluation Framework
di: Santra, Payel, et al.
Pubblicazione: (2026)

Predicting Retrieval Utility and Answer Quality in Retrieval-Augmented Generation
di: Tian, Fangzheng, et al.
Pubblicazione: (2026)

Beyond Correlations: A Downstream Evaluation Framework for Query Performance Prediction
di: Santra, Payel, et al.
Pubblicazione: (2026)

RAQG-QPP: Query Performance Prediction with Retrieved Query Variants and Retrieval Augmented Query Generation
di: Tian, Fangzheng, et al.
Pubblicazione: (2026)

Revisiting Query Variants: The Advantage of Retrieval Over Generation of Query Variants for Effective QPP
di: Tian, Fangzheng, et al.
Pubblicazione: (2025)

Is Relevance Propagated from Retriever to Generator in RAG?
di: Tian, Fangzheng, et al.
Pubblicazione: (2025)

"In-Context Learning" or: How I learned to stop worrying and love "Applied Information Retrieval"
di: Parry, Andrew, et al.
Pubblicazione: (2024)

LLM4Rerank: LLM-based Auto-Reranking Framework for Recommendations
di: Gao, Jingtong, et al.
Pubblicazione: (2024)

Contextual Relevance and Adaptive Sampling for LLM-Based Document Reranking
di: Huang, Jerry, et al.
Pubblicazione: (2025)

LLM4Ranking: An Easy-to-use Framework of Utilizing Large Language Models for Document Reranking
di: Liu, Qi, et al.
Pubblicazione: (2025)

DiffuRank: Effective Document Reranking with Diffusion Language Models
di: Liu, Qi, et al.
Pubblicazione: (2026)

SuiteEval: Simplifying Retrieval Benchmarks
di: Parry, Andrew, et al.
Pubblicazione: (2026)

Exploiting Positional Bias for Query-Agnostic Generative Content in Search
di: Parry, Andrew, et al.
Pubblicazione: (2024)

Evaluating the Explainability of Neural Rankers
di: Pandian, Saran, et al.
Pubblicazione: (2024)

Reranking with Compressed Document Representation
di: Déjean, Hervé, et al.
Pubblicazione: (2025)

RankArena: A Unified Platform for Evaluating Retrieval, Reranking and RAG with Human and LLM Feedback
di: Abdallah, Abdelrahman, et al.
Pubblicazione: (2025)

Exploring the Role of Diversity in Example Selection for In-Context Learning
di: Kapuriya, Janak, et al.
Pubblicazione: (2025)

QBD-RankedDataGen: Generating Custom Ranked Datasets for Improving Query-By-Document Search Using LLM-Reranking with Reduced Human Effort
di: Gopalakrishnan, Sriram, et al.
Pubblicazione: (2025)

In-Context Learning as an Effective Estimator of Functional Correctness of LLM-Generated Code
di: Das, Susmita, et al.
Pubblicazione: (2025)

LANCER: LLM Reranking for Nugget Coverage
di: Ju, Jia-Huei, et al.
Pubblicazione: (2026)

Leveraging Reference Documents for Zero-Shot Ranking via Large Language Models
di: Li, Jieran, et al.
Pubblicazione: (2025)

A Deep Learning Approach for Selective Relevance Feedback
di: Datta, Suchana, et al.
Pubblicazione: (2024)

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking
di: Jin, Haoxiang, et al.
Pubblicazione: (2025)

DeAR: Dual-Stage Document Reranking with Reasoning Agents via LLM Distillation
di: Abdallah, Abdelrahman, et al.
Pubblicazione: (2025)

ListT5: Listwise Reranking with Fusion-in-Decoder Improves Zero-shot Retrieval
di: Yoon, Soyoung, et al.
Pubblicazione: (2024)

Efficient Listwise Reranking with Compressed Document Representations
di: Déjean, Hervé, et al.
Pubblicazione: (2026)

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