Workshops - SIGIR 2024

July 18, 2024 - Washington DC, USA

The SIGIR 2024 workshop program will host 13 compelling workshops that highlight the breadth of interesting problems being explored in the field of information retrieval and that explore novel ideas and emerging areas in the field.

Full Day Workshops

Half Day Workshops

Third Workshop on Personalization and Recommendations in Search (PaRiS)

Organizers: Sudarshan Lamkhede, Moumita Bhattacharya, Hongning Wang, Hamed Zamani
Abstract: With the proliferation of personal computing devices and a large number of logged-in experiences, search has evolved to a stage with many different product scenarios where personalization plays a crucial role in relevance quality, and user satisfaction. Though search context plays a big role in determining relevance, the utility of a search system for its users can be further enhanced by providing personalized results as well as recommendations within the search context. Hence, this workshop aims to engage in the discussions of algorithmic and system challenges in search personalization and effectively recommending in the search context.

Large Language Model for Evaluation in IR (LLM4Eval)

Organizers: Hossein A. Rahmani, Clemencia Siro Mohammad Aliannejadi, Nick Craswell, Charles L. A. Clarke, Guglielmo Faggioli, Bhaskar Mitra, Paul Thomas, Emine Yilmaz
Abstract: Large language models (LLMs) have demonstrated increasing task-solving abilities not present in smaller models. Utilizing the capabilities and responsibilities of LLMs for automated evaluation (LLM4Eval) has recently attracted considerable attention in multiple research communities. For instance, LLM4Eval models have been studied in the context of automated judgments, natural language generation, and retrieval augmented generation systems. We believe that the information retrieval community can significantly contribute to this growing research area by designing, implementing, analyzing, and evaluating various aspects of LLMs with applications to LLM4Eval tasks. The main goal of LLM4Eval workshop is to bring together researchers from industry and academia to discuss various aspects of LLMs for evaluation in information retrieval, including automated judgments, retrieval-augmented generation pipeline evaluation, altering human evaluation, robustness, and trustworthiness of LLMs for evaluation in addition to their impact on real-world applications. We also plan to run an automated judgment challenge prior to the workshop, where participants will be asked to generate labels for a given dataset while maximising correlation with human judgments. The format of the workshop is interactive, including roundtable and keynote sessions and tends to avoid the one-sided dialogue of a mini-conference. Since SIGIR 2024 will not accommodate remote participation, in addition to the physical workshop at SIGIR 2024, we plan a 90-minute virtual version of the workshop in late July, with its own invited speaker.

The Second Workshop on Generative Information Retrieval (Gen-IR@SIGIR24)

Organizers: Gabriel Bénédict, Donald Metzler, Ruqing Zhang, Andrew Yates, Ziyan Jiang
Abstract: Generative information retrieval (Gen-IR) is a fast-growing interdisciplinary research area that investigates how to leverage advances in generative Artificial Intelligence (AI) to improve information retrieval systems. Gen-IR has attracted interest from the information retrieval, natural language processing, and machine learning communities, among others. Since the dawn of Gen-IR last year, there has been an explosion of Gen-IR systems that have launched and are now widely used. Interest in this area across academia and industry is only expected to continue to grow as new research challenges and application opportunities arise. The goal of this workshop, The Second Workshop on Generative Information Retrieval (Gen-IR @ SIGIR 2024) is to provide an interactive venue for exploring a broad range of foundational and applied Gen-IR research. The workshop will focus on tasks such as generative document retrieval, grounded answer generation, generative recommendation, and generative knowledge graphs, all through the lens of model training, model behavior, and broader issues.

Information Retrieval's Role in RAG Systems (IR-RAG)

Organizers: Fabio Petroni, Federico Siciliano, Fabrizio Silvestri, Giovanni Trappolini
Abstract: In the dynamic world of AI, our workshop spotlights Retrieval Augmented Generation (RAG) systems, emphasizing generative AI's role alongside Information Retrieval (IR). We aim to explore the fusion of generative models and IR, inviting insights that highlight their collaborative potential in RAG. This gathering seeks to foster advancements by discussing research, challenges, and the future of generative AI within RAG, encouraging a rich dialogue among AI enthusiasts. Join us to delve into the synergy between IR and generative models, shaping the next wave of AI innovation.

International Workshop on Algorithmic Bias in Search and Recommendation (BIAS 2024)

Organizers: Alejandro Bellogín, Ludovico Boratto, Styliani Kleanthous, Elisabeth Lex, Francesca Maridina Malloci, Mirko Marras
Abstract: Creating efficient and effective search and recommendation algorithms has been the main objective of industry practitioners and academic researchers over the years. However, recent research has shown how these algorithms trained on historical data lead to models that might exacerbate existing biases and generate potentially negative outcomes. Defining, assessing, and mitigating these biases throughout experimental pipelines is a primary step for devising search and recommendation algorithms that can be responsibly deployed in real-world applications. This workshop aims to collect novel contributions in this field and offer a common ground for interested researchers and practitioners.

Reaching Efficiency in Neural Information Retrieval (ReNeuIR)

Organizers: Maik Fröbe, Joel Mackenzie, Bhaskar Mitra, Franco Maria Nardini, Martin Potthast
Abstract: The third iteration of ReNeuIR aims to bring the community together to debate questions about the efficiency of neural search applications. As part of the workshop, a shared task will collaboratively test and improve a benchmarking framework for efficiency derived from the discussions of the first two iterations of this workshop.

The First Workshop on Agent-based Information Retrieval (AgentIR)

Organizers: Qingpeng Cai, Xiangyu Zhao, Ling Pan, Xin Xin, Jin Huang, Weinan Zhang, Li Zhao, Dawei Yin, Grace Hui Yang
Abstract: Deep reinforcement learning (DRL) has become a promising direction. On the one hand, there have been emerging research works focusing on leveraging DRL for IR tasks. However, the fundamental theory, the challenge for Industrial IR tasks, or the simulations of DRL-based IR systems, has not been deeply investigated. On the other hand, the emerging LLM provides new opportunities for IR systems. We propose the first Agent-based IR workshop at SIGIR 2024, as a continuation from the DRL4IR workshop. We aim to present the recent advances from the agent-based IR’s perspective, to foster novel research, interesting findings, and new applications.

The 2024 SIGIR Workshop on eCommerce (eCom24)

Organizers: Surya Kallumadi, Yubin Kim, Tracy King, Maarten de Rijke, Vamsi Salaka
Abstract: The SIGIR Workshop on eCommerce serves as a platform for publication and discussion of Information Retrieval, NLP and Vision research relative to their applications in the domain of eCommerce. We bring together practitioners and researchers from academia and industry to discuss the challenges and approaches to product search and recommendation in eCommerce. The special theme of this year's workshop is Commerce Search in the Age of Generative AI and LLMs. The workshop also includes a data challenge in collaboration with TREC, to study how end-to-end retrieval systems can be built and evaluated given a large set of products.

The Fifth Workshop on Patent Text Mining and Semantic Technologies (PatentSemTech2024)

Organizers: Ralf Krestel, Hidir Aras, Linda Andersson, Florina Piroi, Allan Hanbury, Dean Alderucci
Abstract: Information retrieval systems for the intellectual property (IP) domain can support patent experts in a variety of daily tasks: from analyzing the patent landscape to support experts in the patenting process and large-scale information extraction. With the 5th edition of this workshop we will provide a platform for researchers and industry to present and learn about novel and emerging technologies for semantic patent retrieval ranging from patent text mining, domain-specific information retrieval to large language models (LLMs) targeting next generation applications and use cases for the IP and related domains.

SIGIR 2024 Workshop on Simulations for Information Access (Sim4IA@SIGIR 2024)

Organizers: Philipp Schaer, Christin Kreutz, Krisztian Balog, Timo Breuer, Norbert Fuhr
Abstract: Simulations in different variations have been used to evaluate information access systems, like search engines, recommender systems, or conversational agents. In the form of the Cranfield paradigm, a simulation setup is well-known in the IR community, but user simulations have recently gained interest. While user simulations help to reduce the complexity of evaluation experiments and help with reproducibility, they can also contribute to a better understanding of users. Building on recent developments in methods and toolkits, Sim4IA aims to bring together researchers and practitioners to form an interactive and engaging forum for discussions on the future perspectives of the field.

The Second Workshop on Large Language Models for Individuals, Groups, and Society (LLM-IGS-II)

Organizers: Michael Bendersky, Cheng Li, Qiaozhu Mei, Vanessa Murdock, Jie Tang, Hongning Wang, Hamed Zamani, Mingyang Zhang, Xingjian Zhang
Abstract: This workshop discusses the cutting-edge developments in research and applications of personalizing large language models (LLMs) and adapting them to the demands of diverse user populations and societal needs. The full-day workshop plan includes several keynotes and invited talks, a poster session and a panel discussion.

First SIGIR 2024 Workshop on Information Retrieval for Climate Impact (MANILA24)

Organizers: Bart van den Hurk, Maarten de Rijke, Flora Salim
Abstract: Climate change is a far-reaching, global phenomenon that will impact many aspects of our society. The evidence base for observed climate impacts is expanding, and the wider climate literature is growing exponentially. How can effective access be provided to the growing body of peer-reviewed literature on climate change impact? The MANILA24 workshop is meant to help build a community around the topic of information retrieval for climate impact and activate its participants to articulate both short-term and long-term research agendas whose purpose is to support climate impact and design actionable challenges for IR researchers.

The 1st Workshop on Multimodal Representation and Retrieval (MRR 2024)

Organizers: Xinliang Zhu, Arnab Dhua, Douglas Gray, I. Zeki Yalniz, Tan Yu, Mohamed H. Elhoseiny, Bryan A. Plummer
Abstract: Multimodal data is available in many applications like e-commerce production listings, social media posts and short videos. However, existing algorithms dealing with those types of data still focus on uni-modal representation learning by vision-language alignment and cross-modal retrieval. In this workshop, we target to bring a new retrieval problem where both queries and documents are multimodal. We will discuss the uniqueness of the problem and the new challenges. It’s a half-day workshop with a keynote talk, oral presentations, and a panel discussion.