
ADM+S researchers present at world leading conference on information retrieval
Author ADM+S Centre
Date 29 April 2026
Researchers from the ARC Centre of Excellence for Automated Decision-Making and Society will present their latest work on information retrieval at SIGIR 2026, one of the world’s leading conferences in the field.
ADM+S researchers will contribute across a wide range of formats and play a key role in shaping the conference program, including the delivery ot tutorials and workshops.
Doctoral abstracts
The doctoral abstracts explore emerging questions around how people interact with search technologies in the age of AI. Topics range from user behaviour in hybrid search environments to the effects of social conformity in human–AI systems, and how generative AI is influencing the way people search for information.
- User Search Behavior and Knowledge Effects in Hybrid Search Environment
Jiaman He - Characterising the Effects of Social Conformity on Information Seeking in Mixed Human-AI Environments
Nethmi Wijesinghe - From Lab to Reality: An Eye-tracking Study of How Users are Influenced to Search in the Era of GenAI
Sara Allawati
Full papers
Full paper presentations cover a diverse set of topics, including the impact of AI-generated search overviews on user behaviour, new methods to mitigate bias in large language model-based question answering, and advances in retrieval-augmented generation systems. Other research examines how to model complex search behaviours and simulate user profiles using AI to improve recommendation systems.
- An Eye Tracking Study: Are AI Overviews Changing Search Behavior?
Sara Allawati, Dana McKay, Mark Sanderson, Paul Thomas, Johanne Trippas - Mitigating Bias in Large Language Model Based Question Answering through Causal Front Door Prompting
Yaqi Yang, Ziqi Xu, Jie Li, Chenglong Ma, Jeffrey Chan, Mark Sanderson, Xin Zheng, Yongli Ren - Understanding and Modeling Heterogeneous Search Behavior
Nuha Abu Onq, Chenglong Ma, Mark Sanderson, Falk Scholer - SRAG: A Lightweight and Specialized Retrieval-augmented Generation System at the Edge
Ruikun Luo, Zihan Xing, Lin Gu, Song Wu, Hai Jin, Xiaoyu Xia - Task-Aware Automated User Profile Generation for Recommendation Simulation Using Large Language Models
Xinye Wanyan, Chenglong Ma, Danula Hettiachchi, Ziqi Xu, Jeffrey Chan
Perspective papers
The Centre’s perspective papers tackle broader challenges in the field, including the limits of current approaches to auditing AI systems and ongoing questions about evaluation standards in information retrieval research.
- Deletion Isn’t Enough: Auditing RAG for Selective Forgetting
Leila Tavakoli and Mark Sanderson - Evaluation validity in information retrieval
Paul Thomas, Nick Craswell, Mark Sanderson, Seth Spielman, Robert Sim and Ryen White
Resource papers
ADM+S researchers are also contributing important new datasets and benchmarking tools through resource papers, supporting the development of more robust and transparent AI systems.
- Auto-Judge: A Cross-Task Benchmark for Comparing LLM Judges for Citation-Grounded RAG Systems
Naghmeh Farzi, Tim Hagen, Eugene Yang, Maik Fröbe, Ronak Pradeep, Hossein A. Rahmani, Xi Wang, Oleg Zendel, Martin Potthast, Laura Dietz - A Sketch+Text Composed Image Retrieval Dataset for Thangka
Jinyu Xu, Yi Sun, Jiangling Zhang, Qing Xie, Daomin Ji, Zhifeng Bao, Jiachen Li, Yanchun Ma, Yongjian Liu
View the 2025 ADM+S Annual Report
Short papers
Short papers further extend this work into areas such as anomaly detection, explainable AI, knowledge tracing and recommendation systems, reflecting the breadth of technical innovation across the Centre.
- Retrieval-Augmented Contrastive Learning for Dynamic Graph Anomaly Detection
kamal berahmand, Saman Forouzandeh, Mehrnoush Mohammadi, Mahdi Jalili - ExODRec: An Explainable Framework for Outlier Detection Model Recommendation
Saba Rabooki, Ziqi Xu, Elham Naghizade - Retrieval-Augmented Contrastive Learning for Knowledge Tracing
kamal berahmand, Mehrnoush Mohammadi, Homa Babai, Hassan Khosravi - Task-Adaptive Retrieval over Multi-Modal Web Histories via Learned Graph Memory
Saman Forouzandeh, kamal berahmand, Mahdi Jalili - One Pass, Any Order: Position-Invariant Listwise Ranking for LLM Recommenders
Ethan Bito, Yongli Ren, Estrid He
Tutorials
Beyond paper presentations, ADM+S researchers will lead two tutorials focused on interdisciplinary collaboration and user simulation in search and recommendation system, key areas for translating technical advances into real-world impact.
- Transdisciplinarity for Human Information Interaction and Retrieval: Strategies for Collaborating Across Research Disciplines to Foster Societal Impact
Lisa M. Given, Joann Cattlin - Verifiable User Simulation for Search and Recommendation Systems
Chenglong Ma, Xinye Wanyan, Danula Hettiachchi, Ziqi Xu, Yongli Ren, Jeffrey Chan - IR for Climate Change Impact
Flora Salim, Maarten de Rijke
Workshops
The Centre is also co-organising two workshops addressing some of the most pressing societal questions in AI. One workshop examines issues of justice, democracy and control over information access platforms, while the other focuses on vulnerabilities in generative AI systems used in information retrieval.
- Justice, Emancipation, Democracy, and Information Access (JEDI): The SIGIR Workshop on Resisting Corporate and Authoritarian Capture of Information Access Platforms
Bhaskar Mitra, Dana Mckay, Michael Ekstrand, Sanne Vrijenhoek, Maria Murray - VulGen: International Workshop on Vulnerabilities in Generative Systems for Information Retrieval
Shuoqi Sun, Sara Allawati, Laura Dietz, Madhurima Khirbat, Bhaskar Mitra, Maarten de Rijke, Damiano Spina
Note to Safari users: If the PDF doesn’t display correctly at first, please refresh the page


