publications

The COALESCE framework extends DBIR principles to AI-powered educational technology development, positioning educators as active co-creators. This study evaluates COALESCE through its application in designing an AI-assisted lesson-planning tool. Our findings show how deep educator involvement supports trust, ownership, and domain-specific improvements in AI-generated content. We discuss implications for participatory AI design and offer a replicable model for context-aware, educator-aligned innovation.

As generative AI (GenAI) models are increasingly explored for educational applications, understanding educator preferences for AI-generated lesson plans is critical for their effective integration into K-12 instruction. This exploratory study compares lesson plans authored by human curriculum designers, a fine-tuned LLaMA-2-13b model trained on K-12 content, and a customized GPT-4 model to evaluate their pedagogical quality across multiple instructional measures: warm-up activities, main tasks, cool-down activities, and overall quality. Using a large-scale preference study with K-12 math educators, we examine how preferences vary across grade levels and instructional components. We employ both qualitative and quantitative analyses. The raw preference results indicate that human-authored lesson plans are generally favored, particularly for elementary education, where educators emphasize student engagement, scaffolding, and collaborative learning. However, AI-generated models demonstrate increasing competitiveness in cool-down tasks and structured learning activities, particularly in high school settings. Beyond quantitative results, we conduct thematic analysis using LDA and manual coding to identify key factors influencing educator preferences. Educators value human-authored plans for their nuanced differentiation, real-world contextualization, and student discourse facilitation. Meanwhile, AI-generated lesson plans are often praised for their structure and adaptability for specific instructional tasks. Findings suggest a human-AI collaborative approach to lesson planning, where GenAI can serve as an assistive tool rather than a replacement for educator expertise in lesson planning. This study contributes to the growing discourse on responsible AI integration in education, highlighting both opportunities and challenges in leveraging GenAI for curriculum development.

This study introduces a practice-informed AI nudging system designed to support responsible, context-aware instructional decision-making during lesson planning. Grounded in a hybrid intelligence framework, the system integrates multiple sources of human insight: individual teacher preferences, collective behavior patterns, and pedagogical research, with computational support from large language models to generate timely and explainable nudges. A co-occurrence network of instructional strategies, derived from annotated teacher-AI interactions, guides contextual nudge generation using behavioral heuristics. Initial analysis shows strong alignment between system recommendations and teachers’ pedagogical goals and values, as well as increased diversity in effective instructional practices. By balancing professional autonomy with evidence-based guidance, this work advances responsible AI in education, contributing an explainable, value-sensitive system that fosters sustainable pedagogical improvement in real-world settings.

This report presents a comprehensive account of the Colleague AI Classroom pilot, a collaborative design (co-design) study that brought generative AI technology directly into real classrooms. In this study, AI functioned as a third agent, an active participant that mediated feedback, supported inquiry, and extended teachers’ instructional reach while preserving human judgment and teacher authority. Over seven weeks in spring 2025, 21 in-service teachers from four Washington State public school districts and one independent school integrated four AI-powered features of the Colleague AI Classroom into their instruction: Teaching Aide, Assessment and AI Grading, AI Tutor, and Student Growth Insights. More than 600 students in grades 6-12 used the platform in class at the direction of their teachers, who designed and facilitated the AI activities. During the Classroom pilot, teachers were co-design partners: they planned activities, implemented them with students, and provided weekly reflections on AI’s role in classroom settings. The teachers’ feedback guided iterative improvements for Colleague AI. The research team captured rich data through surveys, planning and reflection forms, group meetings, one-on-one interviews, and platform usage logs to understand where AI adds instructional value and where it requires refinement.

This study investigates how K-12 educators use generative AI tools in real-world instructional contexts and how large language models (LLMs) can support scalable qualitative analysis of these interactions. Drawing on over 13,000 unscripted educator-AI conversations from an open-access platform, we examine educators’ use of AI for lesson planning, differentiation, assessment, and pedagogical reflection. Methodologically, we introduce a replicable, LLM-assisted qualitative analysis pipeline that supports inductive theme discovery, codebook development, and large-scale annotation while preserving researcher control over conceptual synthesis. Empirically, the findings surface concrete patterns in how educators prompt, adapt, and evaluate AI-generated suggestions as part of their instructional reasoning. This work demonstrates the feasibility of combining LLM support with qualitative rigor to analyze complex educator behaviors at scale and inform the design of AI-powered educational tools. To support transparency and reproducibility, we provide an anonymized code repository containing the analysis pipeline and figuregeneration scripts at https://github.com/review-only-repo-xyz/How-K-12-Educators-Use-AI-LLM-Assisted-Qualitative-Analysis-at-Scale/.

The Colleague AI platform introduces a groundbreaking Rubric Generation function designed to streamline how educators create and use rubrics for instructional and assessment purposes. This feature uses artificial intelligence (AI) to produce standards-based rubrics tailored to course content for formative and summative evaluations. By automating this traditionally time-intensive process, Colleague AI empowers educators to focus on enhancing learning outcomes, personalizing content, and ensuring clarity in expectations for students. This article explores the functionality, implementation, and potential of the Rubric Generation function. We also discuss challenges in implementation and offer future directions for its scaling and impact.

As educational settings increasingly integrate artificial intelligence (AI), understanding how AI tools identify – and adapt their responses to – varied educational contexts becomes paramount. This study examines conversational AI’s effectiveness in supporting K12 mathematics education across various educational contexts. Through qualitative content analysis we identify educational contexts and key instructional needs present in educator prompts and assess AI’s responsiveness. Our findings indicate that educators focus their AI conversations on assessment methods, how to set the cognitive demand level of their instruction, and strategies for making meaningful real-world connections. However, educators’ conversations with AI about instructional practices do vary across revealed educational contexts; they shift their emphasis to tailored, rigorous content that addresses their students’ unique needs. Educators often seek actionable guidance from AI and reject responses that do not align with their inquiries. While AI can provide accurate, relevant, and useful information when educational contexts or instructional practices are specified in conversation queries, its ability to consistently adapt responses along these evaluation dimensions varies across different educational settings. Significant work remains to realize the response differentiating potential of conversational AI tools in complex educational use cases. This research contributes insights into developing AI tools that are responsive, proactive, and anticipatory, adapting to evolving educational needs before they are explicitly stated, and provides actionable recommendations for both developers and educators to enhance AI integration in educational practices.

19 K-12 teachers participated in a co-design pilot study of an AI education platform, testing assessment grading. Teachers valued AI’s rapid narrative feedback for formative assessment but distrusted automated scoring, preferring human oversight. Students appreciated immediate feedback but remained skeptical of AI-only grading, highlighting needs for trustworthy, teacher-centered AI tools.

This study examines the impact of AI tools on K-12 math lesson plan quality, addressing teachers’ instructional challenges. Using mixed methods, including descriptive analysis, topic modeling, and interviews, we identified high-quality lesson plan features and explored how teachers use AI to refine content. Findings show teachers generally emphasize student collaboration, inclusivity, and formative assessments, with varying focuses across educational levels. Additionally, AI significantly aids in improving cognitive engagement, promoting inclusivity, and streamlining lesson preparation. While teachers grow with AI, gaps in teacher awareness of AI capabilities persist. Therefore, enhancing AI tools with domain-specific knowledge and increasing teacher professional development for educational technology integration can lead to both more effective AI tool development and more inclusive and engaging math education.

In this report, we share findings from a nationally representative survey of US public school math and science teachers, examining current generative AI (GenAI) use, perceptions, constraints, and institutional support. We show trends in math and science teacher adoption of GenAI, including frequency and purpose of use. We describe how teachers use GenAI with students and their beliefs about GenAI’s impact on student learning. We share teachers’ reporting on the school and district support they are receiving for GenAI learning and implementation, and the support they would like schools and districts to provide, and close with implications for policy, practice, and research. Given the rapid pace of GenAI development and growing pressure on schools to integrate emerging technologies, these findings offer timely insights into how frontline educators are navigating this shift in practice.

This chapter explores the emerging field of adopting artifical intelligence (AI)/machine learning (ML)-powered textual analysis for instructional improvement within the structure of the Instructional Core Framework. It reviews existing studies on AI/ML applications in analyzing teacher, student, and content data, emphasizing the transformative potential of technologies like large language models (LLMs) and generative AI in enhancing instructional efficiency and effectiveness. Through case studies, it illustrates how these technologies can provide actionable insights and generate new instructional materials, thereby advancing professional development, classroom observations, student assessments, and content analysis. The chapter concludes with future research directions, advocating for the integration of AI/ML methodologies with educational domain knowledge to foster an adaptive, inclusive, and equitable educational ecosystem.

A recommender system is tasked with effectively analyzing a user’s preferences and interactions to provide personalized recommendations. This calls for extracting and connecting various heterogeneous data while preserving their temporal relations. Graph neural networks (GNNs) have proven to be highly suitable in recommendation systems for connecting different types of user behavioral signals. However, they inherently lack ability to capture temporal aspects of underlying data. This shortcoming prevents them from explicating and utilizing task information, which is shown to be instrumental in many information retrieval applications. To overcome this limitation, we propose a new Task-based Graph Neural Network model (TGNN) focusing on identifying users’ underlying tasks within their temporal multi-behavior, specifically in each session. The model consists of three modules: (1) a sequential meta-path module that captures a temporal sequence of users’ behaviors; (2) a graph neural network layer that models the relationships between different information items and users into task representations; and (3) a recommendation layer that utilizes a collaborative filtering method to generate top-N recommendations based on the model’s comprehension of users’ tasks. The novelty of our approach lies in understanding users’ tasks through their temporal behavior, enabling more accurate personalization. The results of evaluative experiments on three publicly available datasets demonstrate the effectiveness of our task-based recommendation model compared to 10 baselines and indicate a promising research direction for task-oriented recommender systems.

Teachers increasingly rely on generative AI to support lesson planning, yet general-purpose models such as ChatGPT often fall short in mathematical rigor, pedagogical alignment, and task specificity. This study examines whether specialized AI models, fine-tuned with domain knowledge and expert-labeled data, can better support K-12 mathematics lesson design. We conducted a controlled evaluation with 20 experienced math teachers, comparing lesson plans created by human curriculum designers, a customized GPT-4 model, and a fine-tuned LLaMA-2-13B model across elementary, middle, and high school levels. Teachers assessed lesson components including warm-ups, main tasks, cool-down activities, and overall instructional quality. Results show that while human-created lessons remain preferred overall—particularly at the elementary level—AI-generated materials perform competitively in secondary education contexts. Notably, AI-generated cool-down activities were consistently favored, and the fine-tuned LLaMA model matched or outperformed human lessons in high-school main task quality. These findings suggest that domain-specific fine-tuning enables AI systems to meaningfully augment teacher workflows, offering a cost-effective pathway toward high-quality, pedagogically aligned instructional support rather than wholesale replacement of human expertise.

Explore the transformative power of AI in K-12 education with our session on Colleague.AI – a cutting-edge tool designed to enhance teaching effectiveness and administrative efficiency. Discover how Colleague.AI customizes educational content and assessments to meet diverse student needs, supports ongoing teacher professional development, and streamlines administrative tasks. This session will demonstrate practical applications of AI that can elevate educational practices, making teaching more impactful and efficient and transforming learning environments and outcomes.

A computing system for identifying tasks at risk in a collaborative project includes one or more processors configured to execute, during an inference-time phase, a collaborative project management program and a machine learning model. The collaborative project management program is configured to receive telemetry data associated with a task, process the telemetry data based at least in part on one or more task attributes, and output at least one feature associated with the task. The machine learning model is configured to receive, as inference-time input, the at least one feature associated with the task, and, responsive to receiving the at least one feature, output a risk prediction for the task. The system is configured to output an alert when the task is predicted to be at risk of not being completed by a predetermined due date.

Search behaviors are usually motivated by some task that prompts users into the search process. Complex tasks often initiate long, evolving, interactive search processes with shifting goals and cognitive focus at different search stages. Users’ search strategies are influenced by their search motivation, encountered problems, and cognitive focus or state of knowledge at these search stages. However, existing search systems are primarily designed to optimize one request at a time, ignoring the underlying overarching task, shifting task phases and sub-tasks with users’ cognitive focus, or even the holistic nature of a task-based search session. Although a set of descriptive and theoretical models of the search process can be found in the literature that characterizes tasks, there is a gap in research focused on exploiting dynamic task characteristics in search personalization processes. More importantly, there is a lack of support for users to complete their tasks in an adaptive, dynamic way. To address this issue, this dissertation adopts a multi-disciplinary, human-centered approach and applies a mixed-methods design-based approach to meet three broad objectives: First, develop a conceptual framework for understanding how different types of tasks trigger specific information needs that can lead to different methods and strategies for seeking different forms of information and information sources and, in the due process, identify any barriers they perceive and potential help they choose to overcome those limitations; Second, apply new computational models to construct unified task representations using underlying search behavioral signals that can be transferable and functional to any task circumstances; and Third make existing search and retrieval systems more responsible and efficient to meet the changing state of users’ cognitive focus during the search process by using knowledge gained about users’ tasks and problems. Specifically, this dissertation aims to develop a task-information need-strategy-problem-based task representation that can be leveraged in search and retrieval models to provide task-based supports in different information formats, thus empowering users to make informed decisions about different aspects of their lives by providing information more relevant to their current task state. The result of this study is a step towards developing task-aware intelligent systems capable of supporting users at each stage of their complex task-completion process.

Despite the considerable advancements in modern search systems for assisting users in search tasks of varying types, support for complex tasks that call for multi-round interactions remains challenging. Identifying users’ tasks is essential to understanding their evolving information needs and search goals during search sessions to simulate and achieve real-time adaptive search retrievals; thus, it is a crucial research thrust in interactive information retrieval (IIR). While a series of descriptive and formal models have been proposed to characterize complex information search sessions, only a few focus on leveraging dynamic task features in search personalizations to support users in different task stages in an adaptive fashion. This preliminary study presents a heterogeneous graph neural network model for extracting and representing tasks to better understand users’ interactive search processes by connecting tasks with search interactions. Our approach’s novelty lies in our application of task representation learning, which enables systems to extract hidden task information from users’ search behaviors. The results of our evaluative experiments on TREC Session track data highlight the value of our proposed task representation model and illustrate a promising research direction on task-oriented intelligent systems.

The importance of tasks in information retrieval (IR) has been long argued for, addressed in different ways, often ignored, and frequently revisited. For decades, scholars made a case for the role that a user’s task plays in how and why that user engages in search and what a search system should do to assist. But for the most part, the IR community has been too focused on query processing and assuming a search task to be a collection of user queries, often ignoring if or how such an assumption addresses the users accomplishing their tasks. With emerging areas of conversational agents and proactive IR, understanding and addressing users’ tasks has become more important than ever before. In this paper, we provide various perspectives on where the state-of-the-art is with regard to tasks in IR, what are some of the bottlenecks in deriving and using task information, and how do we go forward from here. In addition to covering relevant literature, the paper provides a synthesis of historical and current perspectives on understanding, extracting, and addressing task-focused search. To ground ongoing and future research in this area, we present a new framing device for tasks using a tree-like structure and various moves on that structure that allow different interpretations and applications. Presented as a combination of synthesis of ideas and past works, proposals for future research, and our perspectives on technical, social, and ethical considerations, this paper is meant to help revitalize the interest and future work in task-based IR.

For users working on a complex search task, it is common to address different goals at various stages of the task through query iterations. While addressing these goals, users go through different task states as well. Understanding these task states latent under users’ interactions is crucial in identifying users’ changing intents and search behaviors to simulate and achieve real-time adaptive search recommendations and retrievals. However, the availability of sizeable real-world web search logs is scarce due to various ethical and privacy concerns, thus often challenging to develop generalizable task-aware computation models. Furthermore, session logs with task state labels are rarer. For many researchers who lack the resources to directly and at scale collect data from users and conduct a time-consuming data annotation process, this becomes a considerable bottleneck to furthering their research. Synthetic search sessions have the potential to address this gap. This paper shares a parsimonious model to simulate synthetic web search sessions with task state information, which interactive information retrieval (IIR) and search personalization studies could utilize to develop and evaluate task-based search and retrieval systems.

Colonialism has had direct impacts on the transmission of American Indian and Alaska Native (AIAN) knowledge systems. Spaces of higher education continue to create challenges for Indigenous students, especially through the disconnection between Native knowledges and the dominant knowledge being taught. These challenges are reflected in the educational attainment disparities between AIAN and non-Indigenous students in the United States and Canada. To address these issues, we emphasize the significance of promoting ethical approaches to Indigenous research and embracing Indigenous ways of knowing. We examine how combining a directed research group (DRG) with a Knowledge Family approach can shift Indigenous experiences with higher education knowledge production. We describe the structure and goals of the DRG Knowledge Families program, which provides support and resources for Indigenous students while fostering meaningful relationships between Indigenous and non-Indigenous researchers. The DRG Knowledge Families approach integrates research opportunities for Indigenous students, focusing on Indigenous knowledge systems and research methodologies. Ultimately this approach aims to create research spaces that value Native knowledge, center community needs, and support the success of Indigenous students.

The varieties of information seeking behavior encompass a range of practices and constructs such as the realization of an information need, selecting the nature of information, as well as information sources. Most of the past works have studied various constructs of the information seeking process, i.e., information, information need, and information sources individually. However, a person forms and re-forms his or her information seeking strategy based on continually shifting values of these dimensions associated with information seeking. This preliminary study conducted a survey with 15 search scenarios and multiple-choice characteristics completed by 114 Amazon’s Mechanical Turk workers to find out more about how these constructs play a role in people’s preferences regarding information seeking strategies. The study took an exploratory and inferential research approach to investigate how different forms of information and information needs might lead to different information sources by building binary classification models. The results show that the choice of sources can be predicted (with 80% accuracy) if the information need, representation, and form of information are apparent.

Most of the existing search and recommender systems do not adequately support complex search tasks. However, according to the theories and empirical evidence from interactive information seeking and retrieval studies, in people’s search behaviors, actions, and outcomes, tasks that trigger the information search process in the first place generate different search actions. Also, defined successes and failures to find information and accomplish tasks are relative to the motivating task end goals, rather than the fulfillment of subtasks and goals of query segments along the search process. Based on this idea, the primary purpose of the proposed research is to explore how to leverage users’ search behaviors and actions in developing methods to construct task representations that can be applied in all search contexts by conducting field studies. Then based on the data collected from the user studies, evaluate the task representations in designing search and recommendation techniques in naturalistic settings to examine the extent to which the context-independent task approach can approximate users’ actual tasks and provide task-specific recommendations. The research will adopt a multi-disciplinary, multi-method approach with human-centered ML-based techniques in the process. The outcomes can help us better understand users’ tasks and thus have implications for the task, user modeling, and system recommendations design.

In this exploratory study, we examine how American Indian and Alaska Native (AIAN) governments and organizations are using social media to share critical health information about coronavirus disease 2019 (COVID-19) with their citizens. Through a thematic analysis of 119 public Facebook posts made by Tribal governments and organizations, we identified three broad categories and 13 subthemes. Tribal governments and organizations created risk communication material for their respective communities that fell under (1) risk reduction,(2) meeting community members’ needs, and (3) staying connected to community and culture. Our findings suggest that through social media AIAN communities and organizations played a crucial role in disseminating reliable culturally adapted risk communication and vital community information to Tribal citizens during the COVID-19 pandemic. Such communication included clear illustrations, posts and messages about the importance of masking up, social distancing and washing one’s hands; mandated border closures; and suggestions for maintaining a sense of connectedness with community. By doing so they are filling a gap that ensures their communities receive the relevant information they need to mitigate and manage risks. In order to understand how to better meet community needs, more work is needed to improve the wellbeing and visibility of AIAN people in the areas of health disparities, technology, social media, and the many impacts of COVID-19.

Complex search tasks that involve uncertain solution space and multi-round search iterations are integral to everyday life and information-intensive workplace practices, affecting how people learn, work, and resolve problematic situations. However, current search systems still face plenty of challenges when applied in supporting users engaging in complex search tasks. To address this issue, we seek to explore the dynamic nature of complex search tasks from process-oriented perspective by identifying and predicting implicit task states. Specifically, based upon the Web search logs and user annotation data (regarding information seeking intentions in local search steps, in-situ search problems, and help needed) collected from 132 search sessions in two controlled lab studies, we developed two task state frameworks based on intention state and problem-help state respectively and examined the connection between task states and search behaviors. We report that (1) complex search tasks of different types can be deconstructed and disambiguated based on the associated nonlinear state transition patterns; and (2) the identified task states that cover multiple subtle factors of user cognition can be predicted from search behavioral signals using supervised learning algorithms. This study reveals the way in which complex search tasks are unfolded and manifested in users’ search interactions and paves the way for developing state-aware adaptive search supports and system evaluation frameworks.

Information need is one of the most fundamental aspects of information seeking, which traditionally conceptualizes as the initiation phase of an individual’s information seeking behavior. However, the very elusive and inexpressible nature of information need makes it hard to elicit from the information seeker or to extract through an automated process. One approach to understanding how a person realizes and expresses information need is to observe their seeking behaviors, to engage processes with information retrieval systems, and to focus on situated performative actions. Using Dervin’s Sense-Making theory and conceptualization of information need based on existing studies, the work reported here tries to understand and explore the concept of information need from a fresh methodological perspective by examining users’ perceived barriers and desired helps in different stages of information search episodes through the analyses of various implicit and explicit user search behaviors. In a controlled lab study, each participant performed three simulated online information search tasks. Participants’ implicit behaviors were collected through search logs, and explicit feedback was elicited through pre-task and post-task questionnaires. A total of 208 query segments were logged, along with users’ annotations on perceived problems and help. Data collected from the study was analyzed by applying both quantitative and qualitative methods. The findings identified several behaviors – such as the number of bookmarks, query length, number of the unique queries, time spent on search results observed in the previous segment, the current segment, and throughout the session – strongly associated with participants’ perceived barriers and help needed. The findings also showed that it is possible to build accurate predictive models to infer perceived problems of articulation of queries, useless and irrelevant information, and unavailability of information from users’ previous segment, current segment, and whole session behaviors. The findings also demonstrated that by combining perceived problem(s) and search behavioral features, it was possible to infer users’ needed help(s) in search with a certain level of accuracy (78%).

This paper examines how individuals judge the accuracy, adequacy, relevance, and trustworthiness of different types of impersonal and interpersonal information sources and how task type influences their evaluation process. 53 participants from diverse backgrounds recruited via Amazon»s Mechanical Turk performed four simulated information seeking tasks. This study analyzed the data collected from participants» self-reported information seeking experiences in online logbooks and follow-up semi-structured interviews with 23 participants by applying both qualitative and quantitative methods. The findings suggest that task type and information source type affect individuals» information quality judgment, and they perceive websites are more accurate than interpersonal sources, though the latter can be trustworthy. Moreover, their understanding of the type of information also affects their quality judgment. For example, they prefer factual information to opinions in some situations.

This paper reports the findings of a study investigating the relationship between information seekers’ selection and use of information sources and their perceptions of information seeking outcomes (i.e., successes and failures) in the context of information seeking barriers as well as contextual factors such as knowledge, emotions and social role. Fifty-three participants performed four simulated information-seeking tasks over a two-day period and reported their experiences and findings in an online logbook. Semi-structured interviews with 23 participants were also conducted in order to examine the issues that arose from the logbook. Data collected from the study were analyzed by applying both qualitative and quantitative methods. The findings suggest that use of impersonal sources provides a higher likelihood of successful outcomes in information seeking episodes compared to interpersonal sources. Meanwhile, interpersonal sources were found to be more effective in providing personalized information. Moreover, there were no significant associations among users’ education, cognitive and emotional characteristics, and other contextual factors and successes and failures in information seeking. Lastly, constraints such as, lack of help from people, unreliable information, and time limitation seemed to influence information seeking outcomes and increase the chances of unsuccessful results.

Information source selection is essential to individuals’ information seeking behaviors. Existing studies have focused on the criteria seekers employ when choosing information sources, such as sources’ accessibility and quality, as well as the contextual factors that shape a seeker’s selection. However, existing findings are somewhat conflicting and lack in-depth understanding of the reasons behind individuals’ choices. The study reported here invited 53 participants from diverse backgrounds to perform simulated information seeking tasks over a two-day period and to report their experiences and findings in an online logbook. Semi-structured interviews with 23 of them were also conducted in order to examine the issues that arose from the logbooks. Our preliminary findings present several factors associated with participants’ choices between impersonal and interpersonal sources. While interpersonal sources are deemed to be more suitable in capturing the context of an information query and providing personalized information, impersonal sources are found to be more accessible under a time constraint while depicting no emotion towards sensitive issues.

This half-day workshop aims to enhance the Library and Information Science (LIS) community’s engagement with Large Language Models (LLMs) such as ChatGPT, LLaMA, BERT, and other advanced artificial intelligence (AI) technologies. We seek to foster collaboration among researchers, practitioners, educators and students for the impactful integration of LLMs within LIS fields. The workshop will enable attendees to share their experiences evaluating and applying LLMs in various professional activities and highlight challenges and opportunities from the LIS perspectives. Through a mix of a keynote talk, four paper presentations, a series of lightning talks, and two rounds of collaborative discussions, this workshop aims to contribute to the development of evidence-based strategies for integrating LLMs into LIS research, practice, and education. This workshop is sponsored by SIG AI. Additional registration fee applies.