Large language models for information retrieval: A survey

Y Zhu, H Yuan, S Wang, J Liu, W Liu, C Deng… - arXiv preprint arXiv …, 2023 - arxiv.org
As a primary means of information acquisition, information retrieval (IR) systems, such as
search engines, have integrated themselves into our daily lives. These systems also serve …

" According to...": Prompting Language Models Improves Quoting from Pre-Training Data

O Weller, M Marone, N Weir, D Lawrie… - arXiv preprint arXiv …, 2023 - arxiv.org
Large Language Models (LLMs) may hallucinate and generate fake information, despite pre-
training on factual data. Inspired by the journalistic device of" according to sources", we …

Can Query Expansion Improve Generalization of Strong Cross-Encoder Rankers?

M Li, H Zhuang, K Hui, Z Qin, J Lin… - Proceedings of the 47th …, 2024 - dl.acm.org
Query expansion has been widely used to improve the search results of first-stage retrievers,
yet its influence on second-stage, cross-encoder rankers remains under-explored. A recent …

Genqrensemble: Zero-shot llm ensemble prompting for generative query reformulation

KD Dhole, E Agichtein - European Conference on Information Retrieval, 2024 - Springer
Query Reformulation (QR) is a set of techniques used to transform a user's original search
query to a text that better aligns with the user's intent and improves their search experience …

NevIR: negation in neural information retrieval

O Weller, D Lawrie, B Van Durme - arXiv preprint arXiv:2305.07614, 2023 - arxiv.org
Negation is a common everyday phenomena and has been a consistent area of weakness
for language models (LMs). Although the Information Retrieval (IR) community has adopted …

Towards Optimizing and Evaluating a Retrieval Augmented QA Chatbot using LLMs with Human in the Loop

A Afzal, A Kowsik, R Fani, F Matthes - arXiv preprint arXiv:2407.05925, 2024 - arxiv.org
Large Language Models have found application in various mundane and repetitive tasks
including Human Resource (HR) support. We worked with the domain experts of SAP SE to …

Enhancing Asymmetric Web Search through Question-Answer Generation and Ranking

D Ye, J Liu, J Fan, B Tian, T Zhou, X Chen… - Proceedings of the 30th …, 2024 - dl.acm.org
This paper addresses the challenge of the semantic gap between user queries and web
content, commonly referred to as asymmetric text matching, within the domain of web …

Corpus-Steered Query Expansion with Large Language Models

Y Lei, Y Cao, T Zhou, T Shen, A Yates - arXiv preprint arXiv:2402.18031, 2024 - arxiv.org
Recent studies demonstrate that query expansions generated by large language models
(LLMs) can considerably enhance information retrieval systems by generating hypothetical …

QueryExplorer: An Interactive Query Generation Assistant for Search and Exploration

KD Dhole, S Bajaj, R Chandradevan… - arXiv preprint arXiv …, 2024 - arxiv.org
Formulating effective search queries remains a challenging task, particularly when users
lack expertise in a specific domain or are not proficient in the language of the content …

Defending Against Misinformation Attacks in Open-Domain Question Answering

O Weller, A Khan, N Weir, D Lawrie… - arXiv preprint arXiv …, 2022 - arxiv.org
Recent work in open-domain question answering (ODQA) has shown that adversarial
poisoning of the search collection can cause large drops in accuracy for production systems …