Related papers: Evaluating the Robustness of Retrieval Pipelines w…
Retrieval-Augmented Generation (RAG) systems critically depend on retrieval quality, yet no systematic comparison of modern retrieval methods exists for heterogeneous documents containing both text and tabular data. We benchmark ten…
Generative search engines have the potential to transform how people seek information online, but generated responses from existing large language models (LLMs)-backed generative search engines may not always be accurate. Nonetheless,…
Considering the multimodal signals of search items is beneficial for retrieval effectiveness. Especially in web table retrieval (WTR) experiments, accounting for multimodal properties of tables boosts effectiveness. However, it still…
Efficiently optimizing multi-model inference pipelines for fast, accurate, and cost-effective inference is a crucial challenge in machine learning production systems, given their tight end-to-end latency requirements. To simplify the…
Reasoning-Intensive Retrieval (RIR) targets retrieval settings where relevance is mediated by latent inferential links between a query and supporting evidence, rather than semantic similarity. Motivated by the emergent reasoning abilities…
Large language models are powerful text processors and reasoners, but are still subject to limitations including outdated knowledge and hallucinations, which necessitates connecting them to the world. Retrieval-augmented large language…
As financial applications of large language models (LLMs) gain attention, accurate Information Retrieval (IR) remains crucial for reliable AI services. However, existing benchmarks fail to capture the complex and domain-specific information…
A range of approaches have been proposed for estimating the accuracy or robustness of the measured performance of IR methods. One is to use bootstrapping of test sets, which, as we confirm, provides an estimate of variation in performance.…
In real-world Information Retrieval (IR) experiments, the Evaluation Environment (EE) is exposed to constant change. Documents are added, removed, or updated, and the information need and the search behavior of users is evolving.…
Large language models augmented with task-relevant documents have demonstrated impressive performance on knowledge-intensive tasks. However, regarding how to obtain effective documents, the existing methods are mainly divided into two…
Establishing a docker-based replicability infrastructure offers the community a great opportunity: measuring the run time of information retrieval systems. The time required to present query results to a user is paramount to the users…
With the advancement of information retrieval (IR) technologies, robustness is increasingly attracting attention. When deploying technology into practice, we consider not only its average performance under normal conditions but, more…
Intelligent document processing pipelines extract structured entities (tables, images, and text) from documents for use in downstream systems such as knowledge bases, retrieval-augmented generation, and analytics. A persistent limitation of…
Retriever-augmented generation (RAG) has become a widely adopted approach for enhancing the factual accuracy of large language models (LLMs). While current benchmarks evaluate the performance of RAG methods from various perspectives, they…
In evaluation campaigns, participants often explore variations of popular, state-of-the-art baselines as a low-risk strategy to achieve competitive results. While effective, this can lead to local "hill climbing" rather than more radical…
Retrieval systems are increasingly used in biomedical and clinical natural language processing applications, yet practical guidance for researchers building such systems is limited. In this work, we provide such guidance through an…
With the rise of long-context language models (LMs) capable of processing tens of thousands of tokens in a single context window, do multi-stage retrieval-augmented generation (RAG) pipelines still offer measurable benefits over simpler,…
Retrieval-augmented generation (RAG) pipelines have become the de-facto approach for building AI assistants with access to external, domain-specific knowledge. Given a user query, RAG pipelines typically first retrieve (R) relevant…
Pre-trained language models like BERT have achieved great success in a wide variety of NLP tasks, while the superior performance comes with high demand in computational resources, which hinders the application in low-latency IR systems. We…
Large language models (LLMs) are incredible and versatile tools for text-based tasks that have enabled countless, previously unimaginable, applications. Retrieval models, in contrast, have not yet seen such capable general-purpose models…