相关论文: Fusion-in-T5: Unifying Document Ranking Signals fo…
We propose ListT5, a novel reranking approach based on Fusion-in-Decoder (FiD) that handles multiple candidate passages at both train and inference time. We also introduce an efficient inference framework for listwise ranking based on m-ary…
Recently, substantial progress has been made in text ranking based on pretrained language models such as BERT. However, there are limited studies on how to leverage more powerful sequence-to-sequence models such as T5. Existing attempts…
Large-scale e-commerce search must surface a broad set of items from a vast catalog, ranging from bestselling products to new, trending, or seasonal items. Modern systems therefore rely on multiple specialized retrieval channels to surface…
In this paper, we implement and evaluate a two-stage retrieval pipeline for a course recommender system that ranks courses for skill-occupation pairs. The in-production recommender system BrightFit provides course recommendations from…
The 2025 TREC Interactive Knowledge Assistance Track (iKAT) featured both interactive and offline submission tasks. The former requires systems to operate under real-time constraints, making robustness and efficiency as important as…
Rank fusion is a powerful technique that allows multiple sources of information to be combined into a single result set. However, to date fusion has not been regarded as being cost-effective in cases where strict per-query efficiency…
This paper considers the reading comprehension task in which multiple documents are given as input. Prior work has shown that a pipeline of retriever, reader, and reranker can improve the overall performance. However, the pipeline system is…
Neural information retrieval systems typically use a cascading pipeline, in which a first-stage model retrieves a candidate set of documents and one or more subsequent stages re-rank this set using contextualized language models such as…
Text embedding models serve as a fundamental component in real-world search applications. By mapping queries and documents into a shared embedding space, they deliver competitive retrieval performance with high efficiency. However, their…
In information retrieval, large language models (LLMs) have demonstrated remarkable potential in text reranking tasks by leveraging their sophisticated natural language understanding and advanced reasoning capabilities. However,…
Modern retrieval systems do not rely on a single ranking model to construct their rankings. Instead, they generally take a cascading approach where a sequence of ranking models are applied in multiple re-ranking stages. Thereby, they…
In the rapidly evolving field of e-commerce, the effectiveness of search re-ranking models is crucial for enhancing user experience and driving conversion rates. Despite significant advancements in feature representation and model…
Search systems often employ a re-ranking pipeline, wherein documents (or passages) from an initial pool of candidates are assigned new ranking scores. The process enables the use of highly-effective but expensive scoring functions that are…
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…
Nowadays, according to the increasingly increasing information, the importance of its presentation is also increasing. The internet has become one of the main sources of information for users and their favorite topics. It also provides…
We present a hybrid retrieval system for COVID-19 scientific literature, evaluated on the TREC-COVID benchmark (171,332 papers, 50 expert queries). The system implements six retrieval configurations spanning sparse (SPLADE), dense (BGE),…
Social networks have ensured the expanding disproportion between the face of WWW stored traditionally in search engine repositories and the actual ever changing face of Web. Exponential growth of web users and the ease with which they can…
The results of information retrieval (IR) are usually presented in the form of a ranked list of candidate documents, such as web search for humans and retrieval-augmented generation for large language models (LLMs). List-aware retrieval…
We present the methodology and results of the Deep Retrieval team for subtask 4b of the CLEF CheckThat! 2025 competition, which focuses on retrieving relevant scientific literature for given social media posts. To address this task, we…
Recommender systems today have become an essential component of any commercial website. Collaborative filtering approaches, and Matrix Factorization (MF) techniques in particular, are widely used in recommender systems. However, the natural…