This work proposes two complementary eye tracking methodologies focused on understanding information access. The first study examines the earliest stage of search, the formation of an information need, and the formulation of a query. The second study presents participants with a pre-typed query on a Search Engine Results Page (SERP) containing GenAI content positioned above the traditional ten blue links. Across both studies, the planned analysis examines how user interactions differ from patterns reported in prior literature, and outlines future research directions aimed at deepening our understanding of search behavior in the era of GenAI. By linking visual attention to query behavior across traditional and GenAI-enhanced interfaces, this research contributes toward more intuitive and adaptive search systems that better support evolving information-seeking behavior.

Generative systems are rapidly transforming both academic research and industrial practices. These systems are increasingly integrated into information access and information retrieval (IR) tasks and continue to evolve at a substantial pace. Integrating these models into daily workflows exposes critical vulnerabilities, including adversarial attacks, inherent biases, and negative impacts on user behavior, which can lead to suboptimal or even detrimental outcomes. The VulGen workshop at SIGIR 2026 brings together the IR community and related disciplines (e.g., cyber security) to map this evolving landscape. Through a full day of structured discussion and engagement, we aim to synthesize the current state of research and identify new avenues for future investigation. Information about VulGen is hosted at: https://vulgen-workshop.github.io/SIGIR2026/.

Large Language Models (LLMs) are increasingly used to generate search queries for various Information Retrieval (IR) tasks. However, it remains unclear how these machine-generated queries compare to human-written ones, particularly in terms of diversity and alignment with real user behavior. This paper presents an empirical comparison of LLM- and human-generated queries across multiple dimensions, including lexical diversity, linguistic variation, and retrieval effectiveness. We analyze queries produced by several LLMs and compare them with human queries from two datasets collected five years apart. Our findings show that while LLMs can generate diverse queries, their patterns differ from those observed in human behavior. LLM queries typically exhibit higher surface-level uniqueness but rely less on stopword use and word form variation. They also achieve lower retrieval effectiveness when judged against human queries, suggesting that LLM-generated queries may not always reflect real user intent. These differences highlight the limitations of current LLMs in replicating natural querying behavior. We discuss the implications of these findings for LLM-based query generation and user behavior simulation in IR. We conclude that while LLMs hold potential, they should be used with caution.

Advancements in large language models (LLMs) have changed information retrieval, offering users a more personalised and natural search experience with technologies like OpenAI ChatGPT, Google Bard (Gemini), or Microsoft Copilot. Despite these advancements, research into user tasks and information needs remains scarce. This preliminary work analyses a Google Bard prompt log with 15,023 interactions called the Bard Intelligence and Dialogue Dataset (BIDD), providing an understanding akin to query log analyses. We show that Google Bard prompts are often verbose and structured, encapsulating a broader range of information needs and imperative (e.g., directive) tasks distinct from traditional search queries. We show that LLMs can support users in tasks beyond the three main types based on user intent: informational, navigational, and transactional. Our findings emphasise the versatile application of LLMs across content creation, LLM writing style preferences, and information extraction. We document diverse user interaction styles, showcasing the adaptability of users to LLM capabilities.