Poster Session (Demo)

We demonstrate CEDAR, an application for automating data science (DS) tasks with an agentic setup. Solving DS problems with LLMs is an underexplored area that has immense market value. The challenges are manifold: task complexities, data sizes, computational limitations, and context restrictions. We show that these can be alleviated via effective context engineering. We first impose structure into the initial prompt with DS-specific input fields, that serve as instructions for the agentic system. The solution is then materialized as an enumerated sequence of interleaved plan and code blocks generated by separate LLM agents, providing a readable structure to the context at any step of the workflow. Function calls for generating these intermediate texts, and for corresponding Python code, ensure that data stays local, and only aggregate statistics and associated instructions are injected into LLM prompts. Fault tolerance and context management are introduced via iterative code generation and smart history rendering. The viability of our agentic data scientist is demonstrated using canonical Kaggle challenges.

This paper presents a concept and supporting technology for building RAG-based specialized search engines using open-source frameworks and open web data. The Open Web Index (OWI) provides openly accessible web data, while the modular MOSAIC framework is designed to integrate topical OWI partitions obtained to create search applications tailored to specific use cases. MOSAIC-RAG extends this framework with features based on Large Language Models (LLM), such as summarization or re-ranking. Using this infrastructure, special-purpose and domain-specific search applications can easily be developed and experimented with. For demonstration purposes, we present three example applications in the topical domains of science, health, and arts.

Information retrieval evaluation often suffers from fragmented practices---varying dataset subsets, aggregation methods, and pipeline configurations---that undermine reproducibility and comparability, especially for foundation embedding models requiring robust out-of-domain performance. We introduce SuiteEval, a unified framework that offers automatic end-to-end evaluation, dynamic indexing that reuses on-disk indices to minimise disk usage, and built-in support for major benchmarks (BEIR, LoTTE, MS MARCO, NanoBEIR, and BRIGHT). Users only need to supply a pipeline generator. SuiteEval handles data loading, indexing, ranking, metric computation, and result aggregation. New benchmark suites can be added in a single line. SuiteEval reduces boilerplate and standardises evaluations to facilitate reproducible IR research, as a broader benchmark set is increasingly required.

LectureChat extends the WikiChat conversational AI system by integrating multilingual university lecture transcripts alongside Wikipedia content. The demo showcases a dual retrieval architecture that combines structured encyclopedic knowledge with academic lecture material, leveraging multiple segmentation strategies and cross index reconciliation to improve retrieval quality. The system maintains separate citation spaces for Wikipedia (numeric) and lectures (alphabetic) and preserves temporal provenance for direct video navigation. We present the overall architecture, interaction flow, implementation details, and a reproducibility plan.

We present \textbf{MedNuggetizer} (\url{https://mednugget-ai.de/}\footnote{\url{https://mednugget-ai.de/} \textit{username:} demo, \textit{password:} demo}), a tool for query-driven extraction and clustering of information nuggets from medical documents to support clinicians in exploring underlying medical evidence. Backed by a large language model (LLM), MedNuggetizer performs repeated extractions of information nuggets that are then grouped to generate reliable evidence within and across multiple documents. We demonstrate its utility on the clinical use case of \textit{antibiotic prophylaxis before prostate biopsy} by using major urological guidelines and recent PubMed studies as sources of information. Evaluation by domain experts shows that \textit{MedNuggetizer} provides clinicians and researchers with an efficient way to explore long documents and easily extract reliable, query-focused medical evidence.

Large image collections are typically organized around basic metadata and keyword tags, making content discovery challenging for users seeking specific visual information. Although images may be accompanied by descriptive text, traditional retrieval systems often struggle to bridge the semantic gap between textual descriptions and visual content. In this demo, we present ImageSeek, a hybrid text-to-image retrieval system designed to enhance search effectiveness by combining text and image-based retrieval methods through an asymmetric score adjustment mechanism. The system leverages multilingual CLIP models to encode both visual and textual information, creating unified representations for cross-modal retrieval. Users can search through natural language queries in any supported language, with results ranked using a hybrid approach that treats image-based retrieval as a reliable baseline while harmonizing text-based scores through position-dependent adjustments. The demonstration system operates on a dataset of 42,333 images from the Portuguese Presidency website, providing an appropriate testbed for multimodal retrieval performance. The web application enables direct comparison between conventional CLIP-based retrieval and our hybrid approach, supporting image searches under the same conditions on external platforms, including Google Images and the Arquivo.pt image search system, enabling comparative analysis of the results. To evaluate its effectiveness, ImageSeek allows users to experience differences between retrieval modes while exploring domain-specific visual content.