Abstract
Understanding user behavior in search systems is essential for improving retrieval effectiveness and user satisfaction. While prior research has extensively examined general-purpose web search engines, domain-specific contexts—such as sports information—remain comparatively underexplored. In this study, we analyze over 400,000 interaction log entries from a sports-oriented search engine collected over a two-week period. Our analysis combines classic query-level metrics (e.g., frequency distributions, query lengths) with a detailed examination of click behavior, including entropy-based intent variability and a custom query quality scoring model. Compared to established baselines from general and specialized search environments, we observe a high proportion of new and single-term queries, as well as a notable lack of representativeness among top queries. These findings reveal patterns shaped by the event-driven and entity-centric nature of sports content, offering actionable insights for the design of domain-specific retrieval systems. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

Abstract
Medical case retrieval plays a crucial role in clinical decision-making by enabling healthcare professionals to find relevant cases based on patient records, diagnostic images, and textual descriptions. Given the inherently multimodal nature of medical data, effective retrieval requires models that can bridge the gap between different modalities. Traditional retrieval approaches often rely on unimodal representations, limiting their ability to capture cross-modal relationships. Recent advances in dense model-based techniques have shown promise in overcoming these limitations by encoding multimodal information into a shared latent space, facilitating retrieval based on semantic similarity. This paper investigates the potential of dense models to enhance multimodal search systems. We evaluate various dense model-based approaches to assess which model characteristics have the greatest impact on retrieval effectiveness, using the medical case-based retrieval task from ImageCLEFmed 2013 as a benchmark. Our findings indicate that different dense model approaches substantially impact retrieval effectiveness, and that applying the CombMAX fusion methodto combine their output results further improves effectiveness. Extending context length, however, yielded mixed results depending on the input data. Additionally, domain-specific models—those trained on medical data—outperformed general models trained on broad, non-specialized datasets within their respective fields. Furthermore, when text is the dominant information source, text-only models surpassed multimodal models

Abstract
Dense retrieval models are generally trained using supervised learning approaches for representation learning, which require a labeled dataset (i.e., query-document pairs). However, training such models from scratch is not feasible for most languages, particularly under-resourced ones, due to data scarcity and computational constraints. As an alternative, pretrained dense retrieval models can be fine-tuned for specific downstream tasks or applied directly in zero-shot settings. Given the lack of labeled data for Tetun and the fact that existing dense retrieval models do not currently support the language, this study investigates their application in zero-shot, out-of-distribution scenarios. We adapted these models to Tetun documents, producing zero-shot embeddings, to evaluate their performance across various document representations and retrieval strategies for the ad-hoc text retrieval task. The results show that most pretrained monolingual dense retrieval models outperformed their multilingual counterparts in various configurations. Given the lack of dense retrieval models specialized for Tetun, we combine Hiemstra LM with ColBERTv2 in a hybrid strategy, achieving a relative improvement of +2.01% in P@10, +4.24% in MAP@10, and +2.45% in NDCG@10 over the baseline, based on evaluations using 59 queries and up to 2,000 retrieved documents per query. We propose dual tuning parameters for the score fusion approach commonly used in hybrid retrieval and demonstrate that enriching document titles with summaries generated by a large language model (LLM) from the documents' content significantly enhances the performance of hybrid retrieval strategies in Tetun. To support reproducibility, we publicly release the LLM-generated document summaries and run files.

Abstract
Advancements in large language model (LLM)-based conversational assistants have transformed search experiences into more natural and context-aware dialogues that resemble human conversation. However, limited access to interaction log data hinders a deeper understanding of their real-world usage. To address this gap, we analyzed 16,952 prompt logs from 904 unique users of Labadain Chat, an LLM-based conversational assistant designed for Tetun speakers, to uncover patterns in user search behavior, engagement, and intent. Our findings show that most users (29.87%) spent between one and five minutes per session, with an average of 43 unique daily users. The majority (93.97%) submitted multiple prompts per session, with an average session duration of 16.9 minutes. Most users (95.22%) were based in Timor-Leste, with education and science (28.75%) and health (28.00%) being the most searched topics. We compared our findings with a study on Google Bard logs in English, revealing similar search characteristics-including engagement duration, command-based instructions, and requests for specific assistance. Furthermore, a comparison with two conventional search engines suggests that LLM-based conversational systems have influenced user search behavior on traditional platforms, reflecting a broader trend toward command-driven queries. These insights contribute to a deeper understanding of how user search behavior evolves, particularly within low-resource language communities. To support future research, we publicly release LabadainLog-17k+, a dataset of over 17,000 real-world user search logs in Tetun, offering a unique resource for investigating conversational search in this language.

Abstract

Abstract
Heterogeneous CPU-FPGA C/C++ applications may rely on High-level Synthesis (HLS) tools to generate hardware for critical code regions. As typical HLS tools have several restrictions in terms of supported language features, to increase the size and variety of offloaded regions, we propose several code transformations to improve synthesizability. Such code transformations include: struct and array flattening; moving dynamic memory allocations out of a region; transforming dynamic memory allocations into static; and asynchronously executing host functions, e.g., printf(). We evaluate the impact of these transformations on code region size using three realworld applications whose critical regions are limited by nonsynthesizable C/C++ language features.