SCAI (https://scai.info) celebrates its 10th anniversary this year and we would like to invite our core research community to join us. Since our first workshop started back at ICTIR 2017 in Amsterdam, we came a long way and would like to use this opportunity to reflect on it together. With the advent of large language models, conversational AI has emerged as a primary paradigm for search-intensive tasks. However, despite the vast success of conversational AI, there are major shortcomings in existing solutions that offer promising opportunities for the next breakthroughs which we would like to promote further. The focus of this edition will be on the personalization of conversational search systems, with a featured session for the former TREC shared task "Interactive Knowledge Assistance Track" (iKAT) reintroduced this year at SCAI. In combination with a panel discussion, invited presentations and keynote talks from major industry representatives, a lively poster session, and a separate break-out session featuring hands-on evaluation of the top-notch conversational AI systems, we plan for a full-day dense and highly engaging workshop.

Information extraction with LLMs is typically geared toward extracting individual subject-predicate-object (SPO) triples from short factual texts such as Wikipedia or news articles. In contrast, the L3X methodology tackles the task of extracting long lists from long texts: given a target subject S and predicate P, the goal is to extract the complete list of all objects O for which SPO holds. This is especially challenging over long texts, like entire books or large web crawls, where many objects are long-tail entities. We demonstrate L3X, a web-based system designed for this previously unexplored task. L3X comprises of recall-oriented candidate generation using LLMs in RAG mode, with novel methods for ranking and batching passages, followed by precision-oriented scrutinization. Our demo supports exploring multiple configurations, including LLM-only and RAG baselines, showcasing use cases like fiction-character relations from book series (e.g., 50+ friends of Harry Potter) and business relations from web pages (e.g., CEOs of Toyota).

Abstract This paper presents a new task of predicting the coverage of a text document for relation extraction (RE): Does the document contain many relational tuples for a given entity? Coverage predictions are useful in selecting the best documents for knowledge base construction with large input corpora. To study this problem, we present a dataset of 31,366 diverse documents for 520 entities. We analyze the correlation of document coverage with features like length, entity mention frequency, Alexa rank, language complexity, and information retrieval scores. Each of these features has only moderate predictive power. We employ methods combining features with statistical models like TF-IDF and language models like BERT. The model combining features and BERT, HERB, achieves an F1 score of up to 46%. We demonstrate the utility of coverage predictions on two use cases: KB construction and claim refutation.