However, many previous works studied textual and relational retrieval tasks as separate topics.

Modern vision models are trained on very large noisy datasets.

Answering real-world complex queries, such as complex product search, often requires accurate retrieval from semi-structured knowledge bases that involve blend of unstructured (e.g., textual descriptions of products) and structured (e.g., entity relations of products) information. However, many previous works studied textual and relational retrieval tasks as separate topics. To address the gap, we develop STARK, a large-scale Semi-structure retrieval benchmark on Textual and Relational Knowledge Bases. Our benchmark covers three domains: product search, academic paper search, and queries in precision medicine. We design a novel pipeline to synthesize realistic user queries that integrate diverse relational information and complex textual properties, together with their ground-truth answers (items). We conduct rigorous human evaluation to validate the quality of our synthesized queries. We further enhance the benchmark with high-quality human-generated queries to provide an authentic reference. STARK serves as a comprehensive testbed for evaluating the performance of retrieval systems driven by large language models (LLMs). Our experiments suggest that STARK presents significant challenges to the current retrieval and LLM systems, highlighting the need for more capable semi-structured retrieval systems.

Modern vision models are trained on very large noisy datasets. While these models acquire strong capabilities, they may not follow the user's intent to output the desired results in certain aspects, e.g., visual aesthetic, preferred style, and responsibility. In this paper, we target the realm of visual aesthetics and aim to align vision models with human aesthetic standards in a retrieval system. Advanced retrieval systems usually adopt a cascade of aesthetic models as re-rankers or filters, which are limited to low-level features like saturation and perform poorly when stylistic, cultural or knowledge contexts are involved. We find that utilizing the reasoning ability of large language models (LLMs) to rephrase the search query and extend the aesthetic expectations can make up for this shortcoming.

The rapid evolution of the telecommunication industry necessitates efficient troubleshooting processes to maintain network reliability, software maintainability, and service quality. Trouble Reports (TRs), which document issues in Ericsson's production system, play a critical role in facilitating the timely resolution of software faults. However, the complexity and volume of TR data, along with the presence of diverse criteria that reflect different aspects of each fault, present challenges for retrieval systems. Building on prior work at Ericsson, which utilized a two-stage workflow, comprising Initial Retrieval (IR) and Re-Ranking (RR) stages, this study investigates different TR observation criteria and their impact on the performance of retrieval models. We propose \textbf{CREST} (\textbf{C}riteria-specific \textbf{R}etrieval via \textbf{E}nsemble of \textbf{S}pecialized \textbf{T}R models), a criterion-driven retrieval approach that leverages specialized models for different TR fields to improve both effectiveness and interpretability, thereby enabling quicker fault resolution and supporting software maintenance. CREST utilizes specialized models trained on specific TR criteria and aggregates their outputs to capture diverse and complementary signals. This approach leads to enhanced retrieval accuracy, better calibration of predicted scores, and improved interpretability by providing relevance scores for each criterion, helping users understand why specific TRs were retrieved. Using a subset of Ericsson's internal TRs, this research demonstrates that criterion-specific models significantly outperform a single model approach across key evaluation metrics. This highlights the importance of all targeted criteria used in this study for optimizing the performance of retrieval systems.

Effective visualization retrieval necessitates a clear definition of similarity. Despite the growing body of work in specialized visualization retrieval systems, a systematic approach to understanding visualization similarity remains absent. We introduce the Similarity Framework for Visualization Retrieval (Safire), a conceptual model that frames visualization similarity along two dimensions: comparison criteria and representation modalities. Comparison criteria identify the aspects that make visualizations similar, which we divide into primary facets (data, visual encoding, interaction, style, metadata) and derived properties (data-centric and human-centric measures). Safire connects what to compare with how comparisons are executed through representation modalities. We categorize existing representation approaches into four groups based on their levels of information content and visualization determinism: raster image, vector image, specification, and natural language description, together guiding what is computable and comparable. We analyze several visualization retrieval systems using Safire to demonstrate its practical value in clarifying similarity considerations. Our findings reveal how particular criteria and modalities align across different use cases. Notably, the choice of representation modality is not only an implementation detail but also an important decision that shapes retrieval capabilities and limitations. Based on our analysis, we provide recommendations and discuss broader implications for multimodal learning, AI applications, and visualization reproducibility.

Modern vision models are trained on very large noisy datasets.

Test collections are crucial for evaluating Information Retrieval (IR) systems. Creating a diverse set of user queries for these collections can be challenging, and obtaining relevance judgments, which indicate how well retrieved documents match a query, is often costly and resource-intensive. Recently, generating synthetic datasets using Large Language Models (LLMs) has gained attention in various applications. While previous work has used LLMs to generate synthetic queries or documents to improve ranking models, using LLMs to create synthetic test collections is still relatively unexplored. Previous work~\cite{rahmani2024synthetic} showed that synthetic test collections have the potential to be used for system evaluation, however, more analysis is needed to validate this claim. In this paper, we thoroughly investigate the reliability of synthetic test collections constructed using LLMs, where LLMs are used to generate synthetic queries, labels, or both. In particular, we examine the potential biases that might occur when such test collections are used for evaluation. We first empirically show the presence of such bias in evaluation results and analyse the effects it might have on system evaluation. We further validate the presence of such bias using a linear mixed-effects model. Our analysis shows that while the effect of bias present in evaluation results obtained using synthetic test collections could be significant, for e.g.~computing absolute system performance, its effect may not be as significant in comparing relative system performance. Codes and data are available at: https://github.com/rahmanidashti/BiasSyntheticData.

We present Omni-Embed-Nemotron, a unified multimodal retrieval embedding model developed to handle the increasing complexity of real-world information needs. While Retrieval-Augmented Generation (RAG) has significantly advanced language models by incorporating external knowledge, existing text-based retrievers rely on clean, structured input and struggle with the visually and semantically rich content found in real-world documents such as PDFs, slides, or videos. Recent work such as ColPali has shown that preserving document layout using image-based representations can improve retrieval quality. Building on this, and inspired by the capabilities of recent multimodal models such as Qwen2.5-Omni, we extend retrieval beyond text and images to also support audio and video modalities. Omni-Embed-Nemotron enables both cross-modal (e.g., text - video) and joint-modal (e.g., text - video+audio) retrieval using a single model. We describe the architecture, training setup, and evaluation results of Omni-Embed-Nemotron, and demonstrate its effectiveness in text, image, and video retrieval.