Skip to main content
DLab members standing together in front of a green wall at The University of Queensland

Responsible AI research lab · The University of Queensland

Building AI for public good.

DLab is an interdisciplinary research group exploring how data, people, and AI affect each other.

Work with usMeet the team

Our research

Where data, people, and AI meet

We contribute to computational social science, human-computer interaction, machine learning, and information retrieval, with a focus on the risks and harms of AI.

About the lab

  • Perspective-aware LLM evaluation

    We analyse how large language models encode political and demographic perspectives, with a focus on bias, relevance judgments, and summarisation effects.

  • Human-centred data quality

    We combine metadata, crowdsourcing, and information retrieval methods to improve quality assessment and trust in unstructured data workflows.

  • Social media integrity and safety

    We study misinformation, harmful content, and online persuasion, developing methods and tools for fairer and more transparent sociotechnical systems.

Latest publications

Recent work

Our newest papers at venues across information retrieval, natural language processing, and human-AI interaction.

All publications

  • CIKM 2026

    Pietro Bernardelle, Samaneh Mohtadi, Stefano Civelli, Joel Mackenzie, and Gianluca Demartini. LLMs Encode Relevance as a Layer-Wise Cross-Lingual Signal. In: The 35th International ACM Conference on Knowledge and Information Management (CIKM 2026). Rome, Italy, November 2026.

  • CIKM 2026

    Samaneh Mohtadi, Pietro Bernardelle, Joel Mackenzie, and Gianluca Demartini. Persona Conditioning as an Assessor-Sensitivity Probe for LLM-Based IR Evaluation. In: The 35th International ACM Conference on Knowledge and Information Management (CIKM 2026). Rome, Italy, November 2026.

  • EMNLP 2026

    Martin Paul Wessel, Timo Spinde, Jürgen Pfeffer, and Gianluca Demartini. Definitional Sensitivity in Media Bias Detection: A Multi-Definition Dataset and Benchmark. In: The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026) - Findings paper. Budapest, Hungary, October 2026.

  • HCOMP 2026

    Bing Tuo, Tim Miller, and Gianluca Demartini. Easy to Read, Easy to Trust: How Processing Fluency in LLM Explanations Drives Over-Reliance in Hate Speech Moderation. In: The 2026 ACM Conference on Human-AI Complementarity and Alignment (HCOMP 2026). Alexandria, VA, USA, September 2026.

  • IPM

    Pietro Bernardelle, Stefano Civelli, Leon Fröhling, Riccardo Lunardi, Kevin Roitero, Gianluca Demartini. Political Ideology Shifts in Large Language Models. In: Information Processing & Management (IPM), Elsevier. August 2026.

News and stories

From the lab

Conference reports and reflections written by DLab members.

All posts

Life at DLab

A lab that works together

On campus at The University of Queensland, at conferences around the world, and around the lunch table.

View the gallery
  • Large group of DLab members and colleagues at The Web Conference
  • Large DLab group beside a green wall in a campus courtyard
  • DLab researchers receiving a best paper award on stage at The Web Conference
  • DLab members in lab shirts on the lawn of the Great Court at The University of Queensland

Get involved

Work with us

We partner with government, communities, and organisations to build safe and responsible AI systems.

  • Study with us

    Prospective PhD students curious about sociotechnical research on AI.

    Get in touch

  • Visit the lab

    Funded 8 to 12 week research visits in Brisbane for PhD students from other universities.

    Visiting Students Scheme

  • Collaborate

    Government agencies, communities, and organisations seeking research-backed work on safe and responsible AI.

    Start a conversation

Supported by

About our sponsors