Evaluating The Robustness Of Retrieval Pipelines With Query Variation Generators

Abstract

Heavily pre-trained transformers for language modelling, such as BERT, have shown to be remarkably effective for Information Retrieval (IR) tasks, typically applied to re-rank the results of a first-stage retrieval model. IR benchmarks evaluate the effectiveness of retrieval pipelines based on the premise that a single query is used to instantiate the underlying information need. However, previous research has shown that (I) queries generated by users for a fixed information need are extremely variable and, in particular, (II) neural models are brittle and often make mistakes when tested with modified inputs. Motivated by those observations we aim to answer the following question: how robust are retrieval pipelines with respect to different variations in queries that do not change the queries' semantics? In order to obtain queries that are representative of users' querying variability, we first created a taxonomy based on the manual annotation of transformations occurring in a dataset

Stats

• citations27
• S2 citations—
• github stars17
• HF likes0
• heat score13.36
• arxiv keypenha2021evaluating

Related papers

• Scalable And Effective Generative Information Retrieval (2023)10.48
• Generative Retrieval As Dense Retrieval (2023)0.00
• Revisiting Query Variants: The Advantage Of Retrieval Over Generation Of Query Variants For Effective QPP (2025)0.00
• Diagnosing BERT With Retrieval Heuristics (2022)10.21
• Evaluating Embedding Models And Pipeline Optimization For AI Search Quality (2025)0.00
• How Does Generative Retrieval Scale To Millions Of Passages? (2023)10.61
• REFINE On Scarce Data: Retrieval Enhancement Through Fine-tuning Via Model Fusion Of Embedding Models (2024)3.58
• Generalization Properties Of Retrieval-based Models (2022)0.00