Beyond yes and no: Improving zero-shot llm rankers via scoring fine-grained relevance labels

H Zhuang, Z Qin, K Hui, J Wu, L Yan, X Wang… - arXiv preprint arXiv …, 2023 - arxiv.org
Zero-shot text rankers powered by recent LLMs achieve remarkable ranking performance by
simply prompting. Existing prompts for pointwise LLM rankers mostly ask the model to …

Optimization methods for personalizing large language models through retrieval augmentation

A Salemi, S Kallumadi, H Zamani - … of the 47th International ACM SIGIR …, 2024 - dl.acm.org
This paper studies retrieval-augmented approaches for personalizing large language
models (LLMs), which potentially have a substantial impact on various applications and …

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 …

Leveraging llms for unsupervised dense retriever ranking

E Khramtsova, S Zhuang, M Baktashmotlagh… - Proceedings of the 47th …, 2024 - dl.acm.org
In this paper we present Large Language Model Assisted Retrieval Model Ranking
(LARMOR), an effective unsupervised approach that leverages LLMs for selecting which …

Query performance prediction: From ad-hoc to conversational search

C Meng, N Arabzadeh, M Aliannejadi… - Proceedings of the 46th …, 2023 - dl.acm.org
Query performance prediction (QPP) is a core task in information retrieval. The QPP task is
to predict the retrieval quality of a search system for a query without relevance judgments …

Neural query performance prediction using weak supervision from multiple signals

H Zamani, WB Croft, JS Culpepper - The 41st international ACM SIGIR …, 2018 - dl.acm.org
Predicting the performance of a search engine for a given query is a fundamental and
challenging task in information retrieval. Accurate performance predictors can be used in …

A relative information gain-based query performance prediction framework with generated query variants

S Datta, D Ganguly, M Mitra, D Greene - ACM Transactions on …, 2022 - dl.acm.org
Query performance prediction (QPP) methods, which aim to predict the performance of a
query, often rely on evidences in the form of different characteristic patterns in the …

BERT-QPP: contextualized pre-trained transformers for query performance prediction

N Arabzadeh, M Khodabakhsh, E Bagheri - Proceedings of the 30th …, 2021 - dl.acm.org
Query Performance Prediction (QPP) is focused on estimating the difficulty of satisfying a
user query for a certain retrieval method. While most state of the art QPP methods are based …

Multi-stage conversational passage retrieval: An approach to fusing term importance estimation and neural query rewriting

SC Lin, JH Yang, R Nogueira, MF Tsai… - ACM Transactions on …, 2021 - dl.acm.org
Conversational search plays a vital role in conversational information seeking. As queries in
information seeking dialogues are ambiguous for traditional ad hoc information retrieval (IR) …

A study of a gain based approach for query aspects in recall oriented tasks

GM Di Nunzio, G Faggioli - Applied Sciences, 2021 - mdpi.com
Evidence-based healthcare integrates the best research evidence with clinical expertise in
order to make decisions based on the best practices available. In this context, the task of …