[HTML][HTML] Information retrieval meets large language models: a strategic report from chinese ir community

Q Ai, T Bai, Z Cao, Y Chang, J Chen, Z Chen, Z Cheng… - AI Open, 2023 - Elsevier
The research field of Information Retrieval (IR) has evolved significantly, expanding beyond
traditional search to meet diverse user information needs. Recently, Large Language …

Towards query performance prediction for neural information retrieval: challenges and opportunities

G Faggioli, T Formal, S Lupart, S Marchesin… - Proceedings of the …, 2023 - dl.acm.org
In this work, we propose a novel framework to devise features that can be used by Query
Performance Prediction (QPP) models for Neural Information Retrieval (NIR). Using the …

Resources for brewing beir: Reproducible reference models and statistical analyses

E Kamalloo, N Thakur, C Lassance, X Ma… - Proceedings of the 47th …, 2024 - dl.acm.org
BEIR is a benchmark dataset originally designed for zero-shot evaluation of retrieval models
across 18 different domain/task combinations. In recent years, we have witnessed the …

Splate: Sparse late interaction retrieval

T Formal, S Clinchant, H Déjean… - Proceedings of the 47th …, 2024 - dl.acm.org
The late interaction paradigm introduced with ColBERT stands out in the neural Information
Retrieval space, offering a compelling effectiveness-efficiency trade-off across many …

Disentangled modeling of domain and relevance for adaptable dense retrieval

J Zhan, Q Ai, Y Liu, J Mao, X **e, M Zhang… - arxiv preprint arxiv …, 2022 - arxiv.org
Recent advance in Dense Retrieval (DR) techniques has significantly improved the
effectiveness of first-stage retrieval. Trained with large-scale supervised data, DR models …

Resources for brewing BEIR: reproducible reference models and an official leaderboard

E Kamalloo, N Thakur, C Lassance, X Ma… - arxiv preprint arxiv …, 2023 - arxiv.org
BEIR is a benchmark dataset for zero-shot evaluation of information retrieval models across
18 different domain/task combinations. In recent years, we have witnessed the growing …

A novel dual-stage grey-box stacking method for significantly improving the extrapolation performance of ship fuel consumption prediction models

Z Ruan, L Huang, D Li, R Ma, K Wang, R Zhang… - Energy, 2025 - Elsevier
Abstract Ship Fuel Consumption Prediction (SFCP) is the foundation of ship energy
efficiency assessment and optimization. However, existing research neglects to examine the …

Domain Adaptation of Multilingual Semantic Search--Literature Review

A Bringmann, A Zhukova - arxiv preprint arxiv:2402.02932, 2024 - arxiv.org
This literature review gives an overview of current approaches to perform domain adaptation
in a low-resource and approaches to perform multilingual semantic search in a low-resource …

On Generalization for Generative Flow Networks

A Krichel, N Malkin, S Lahlou, Y Bengio - arxiv preprint arxiv:2407.03105, 2024 - arxiv.org
Generative Flow Networks (GFlowNets) have emerged as an innovative learning paradigm
designed to address the challenge of sampling from an unnormalized probability …

Reducing the Footprint of Multi-Vector Retrieval with Minimal Performance Impact via Token Pooling

B Clavié, A Chaffin, G Adams - arxiv preprint arxiv:2409.14683, 2024 - arxiv.org
Over the last few years, multi-vector retrieval methods, spearheaded by ColBERT, have
become an increasingly popular approach to Neural IR. By storing representations at the …